Demographic Data:
cat <- data.table::fread(here::here("data", "DemographicCategories.csv"))
Template Data Analysis:
# Load The Data:
dt <- data.table::fread(here::here("data", "CGCS-Template.csv"))
head(dt)
## Source eType Target Time Weight SourceLocation TargetLocation
## 1: 0 4 -99 -99 -99 NA NA
## 2: 41 0 34 86400 1 NA NA
## 3: 37 0 27 94461 1 NA NA
## 4: 34 1 27 107548 1 5 5
## 5: 41 0 37 127838 1 NA NA
## 6: 34 1 37 137358 1 5 5
## SourceLatitude SourceLongitude TargetLatitude TargetLongitude
## 1: NA NA NA NA
## 2: NA NA NA NA
## 3: NA NA NA NA
## 4: NA NA NA NA
## 5: NA NA NA NA
## 6: NA NA NA NA
tail(dt)
## Source eType Target Time Weight SourceLocation TargetLocation
## 1: 0 5 571970 31536000 80 NA NA
## 2: 0 5 644226 31536000 1000 NA NA
## 3: 0 5 473173 31536000 1000 NA NA
## 4: 0 5 620120 31536000 800 NA NA
## 5: 0 5 575030 31536000 2000 NA NA
## 6: 0 5 621924 31536000 1000 NA NA
## SourceLatitude SourceLongitude TargetLatitude TargetLongitude
## 1: NA NA NA NA
## 2: NA NA NA NA
## 3: NA NA NA NA
## 4: NA NA NA NA
## 5: NA NA NA NA
## 6: NA NA NA NA
# Summarising the Data:
summary(dt)
## Source eType Target Time
## Min. : 0 Min. :0.000 Min. : -99 Min. : -99
## 1st Qu.: 39 1st Qu.:1.000 1st Qu.: 44 1st Qu.:14005495
## Median : 45 Median :5.000 Median : 72 Median :31536000
## Mean : 26210 Mean :3.068 Mean :274951 Mean :23667653
## 3rd Qu.: 59 3rd Qu.:5.000 3rd Qu.:575030 3rd Qu.:31536000
## Max. :620120 Max. :6.000 Max. :657187 Max. :31536000
##
## Weight SourceLocation TargetLocation SourceLatitude
## Min. : -99 Min. :0.000 Min. :0.000 Mode:logical
## 1st Qu.: 1 1st Qu.:3.000 1st Qu.:3.000 NA's:1325
## Median : 70 Median :5.000 Median :4.000
## Mean : 1941 Mean :3.861 Mean :3.585
## 3rd Qu.: 1000 3rd Qu.:5.000 3rd Qu.:5.000
## Max. :200000 Max. :5.000 Max. :5.000
## NA's :1024 NA's :1024
## SourceLongitude TargetLatitude TargetLongitude
## Mode:logical Mode:logical Mode:logical
## NA's:1325 NA's:1325 NA's:1325
##
##
##
##
##
nrow(dt)
## [1] 1325
ncol(dt)
## [1] 11
dt$Source <- as.character(dt$Source)
dt$Target <- as.character(dt$Target)
str(dt$Source)
## chr [1:1325] "0" "41" "37" "34" "41" "34" "27" "27" "41" "37" "41" ...
str(dt$Target)
## chr [1:1325] "-99" "34" "27" "27" "37" "37" "41" "41" "37" "34" "34" ...
# Differentiating between channels:
dt01 <- dt %>% filter(dt$eType == 0 | dt$eType == 1) # Communication Channel
nrow(dt01) # 563
## [1] 563
dt23 <- dt %>% filter(dt$eType == 2 | dt$eType == 3) # Procurement Channel
nrow(dt23) # 18
## [1] 18
dt4 <- dt %>% filter(dt$eType == 4) # Co-authorship Channel
nrow(dt4) # 1
## [1] 1
dt5 <- dt %>% filter(dt$eType == 5) # Demographic Channel
nrow(dt5) # 591
## [1] 691
dt6 <- dt %>% filter(dt$eType == 6) # Travel Channel
nrow(dt6) # 52
## [1] 52
# Analysis of the Communication channel:
glimpse(dt01)
## Observations: 563
## Variables: 11
## $ Source <chr> "41", "37", "34", "41", "34", "27", "27", "41"...
## $ eType <int> 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1...
## $ Target <chr> "34", "27", "27", "37", "37", "41", "41", "37"...
## $ Time <int> 86400, 94461, 107548, 127838, 137358, 137514, ...
## $ Weight <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1...
## $ SourceLocation <int> NA, NA, 5, NA, 5, NA, NA, 5, NA, NA, 5, 5, NA,...
## $ TargetLocation <int> NA, NA, 5, NA, 5, NA, NA, 5, NA, NA, 5, 5, NA,...
## $ SourceLatitude <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ SourceLongitude <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLatitude <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLongitude <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
#unique(dt01)
unique(dt01$eType) # 0 1
## [1] 0 1
unique(dt01$SourceLocation) # NA 5 3 4 0
## [1] NA 5 3 4 0
unique(dt01$TargetLocation) # NA 5 0 3 4
## [1] NA 5 0 3 4
unique(dt01$SourceLatitude) # NA
## [1] NA
unique(dt01$SourceLongitude) # NA
## [1] NA
unique(dt01$TargetLatitude) # NA
## [1] NA
unique(dt01$TargetLongitude) # NA
## [1] NA
unique(dt01$Source)
## [1] "41" "37" "34" "27" "40" "65" "67" "47" "39" "43" "57" "58" "63" "56"
## [15] "45"
unique(dt01$Target)
## [1] "34" "27" "37" "41" "0" "39" "66" "47" "65" "40" "67" "56" "43" "57"
## [15] "58" "63" "45"
dt01 <- subset(dt01, select = -c(SourceLatitude, SourceLongitude)) # SOurce and Target Latitude and Longitude columns removed as all Null.
dt01 <- subset(dt01, select = -c(TargetLatitude, TargetLongitude))
dt01 <- subset(dt01, select = -Weight) # Weight removed as all values 1.
colnames(dt01)
## [1] "Source" "eType" "Target" "Time"
## [5] "SourceLocation" "TargetLocation"
any(dt01$Source) == any(dt01$Target) # True
## Warning in any(dt01$Source): coercing argument of type 'character' to
## logical
## Warning in any(dt01$Target): coercing argument of type 'character' to
## logical
## [1] NA
range(dt01$Source) # 27-67
## [1] "27" "67"
range(dt01$Target) # 0-67
## [1] "0" "67"
range(dt01$Time) # 86400-27222388
## [1] 86400 27222388
# Analysis of the Demographic channel:
glimpse(dt5)
## Observations: 691
## Variables: 11
## $ Source <chr> "2", "2", "510031", "2", "552988", "2", "2", "...
## $ eType <int> 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5...
## $ Target <chr> "630626", "536346", "2", "520660", "2", "56719...
## $ Time <int> 31536000, 31536000, 31536000, 31536000, 315360...
## $ Weight <int> 5000, 1000, 600, 3000, 40000, 4000, 100, 900, ...
## $ SourceLocation <int> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLocation <int> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ SourceLatitude <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ SourceLongitude <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLatitude <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLongitude <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
#unique(dt5)
unique(dt5$eType) # 5
## [1] 5
unique(dt5$SourceLocation) # NA
## [1] NA
unique(dt5$TargetLocation) # NA
## [1] NA
unique(dt5$SourceLatitude) # NA
## [1] NA
unique(dt5$SourceLongitude) # NA
## [1] NA
unique(dt5$TargetLatitude) # NA
## [1] NA
unique(dt5$TargetLongitude) # NA
## [1] NA
unique(dt5$Source)
## [1] "2" "510031" "552988" "27" "29" "31" "33"
## [8] "34" "35" "36" "620120" "37" "38" "39"
## [15] "40" "41" "42" "43" "44" "45" "46"
## [22] "47" "48" "49" "52" "53" "54" "55"
## [29] "56" "57" "58" "59" "60" "61" "62"
## [36] "63" "64" "65" "0"
unique(dt5$Target)
## [1] "630626" "536346" "2" "520660" "567195" "527449" "459381"
## [8] "595298" "466907" "589943" "577992" "537281" "523927" "580426"
## [15] "595581" "642329" "503701" "571970" "644226" "632961" "473173"
## [22] "620120" "621924" "27" "616315" "29" "575030" "503218"
## [29] "31" "33" "34" "35" "36" "37" "38"
## [36] "39" "40" "41" "42" "43" "44" "45"
## [43] "46" "47" "48" "640784" "49" "606730" "52"
## [50] "53" "54" "55" "56" "57" "58" "59"
## [57] "60" "61" "62" "63" "64" "65" "0"
unique(dt5$Weight)
## [1] 5000 1000 600 3000 40000 4000 100 900 2000 400
## [11] 200 20 500 10 700 6000 50000 50 800 300
## [21] 9000 30000 8000 70 10000 40 30 80 20000 60
## [31] 90 200000 7000 2 7 100000 3 6
dt5 <- subset(dt5, select = -c(SourceLocation, TargetLocation, SourceLatitude, SourceLongitude, TargetLatitude, TargetLongitude)) # SOurce and Target Latitude and Longitude columns removed as all Null.
colnames(dt5)
## [1] "Source" "eType" "Target" "Time" "Weight"
#any(dt5$Source) == any(dt5$Target) # True
range(dt5$Source) # 0-620120
## [1] "0" "65"
range(dt5$Target) # 0-644226
## [1] "0" "65"
range(dt5$Time) # 31536000-31536000
## [1] 31536000 31536000
income_cat <- subset(dt5$Source, dt5$Source >= 500000)
unique(income_cat) #Income Categories: 510031(Gifts), 552988(Money Income before Taxes), 620120(Personal Taxes)
## [1] "620120" "60" "61" "62" "63" "64" "65"
expense_cat <- subset(dt5$Target, dt5$Target >= 500000)
sort(unique(expense_cat)) # Expense Categories: 503218(Natural Gas) 503701(Miscellaneous) 520660(Healthcare) 523927(Restaurants) 527449 (Alcohol)
## [1] "60" "606730" "61" "616315" "62" "620120" "621924"
## [8] "63" "630626" "632961" "64" "640784" "642329" "644226"
## [15] "65"
# 536346(Home Maintenance) 537281(HouseKeeping) 567195 (Personal insurance and pensions)
# 571970(Reading) 575030 (Transportation) 577992 (Education) 580426 (Telephone services)
# 589943(Lodging away from home) 595298(Groceries) 595581(Donations) 606730(Entertainment)
# 616315(Apparel and services) 620120(Personal taxes) 621924(Mortgage payments)
# 630626(Rented dwellings) 632961(Personal care products and services)
# 640784(Tobacco) 642329(Household operations) 644226(Property taxes)
hist(dt5$Weight)
unique(dt5$Weight)
## [1] 5000 1000 600 3000 40000 4000 100 900 2000 400
## [11] 200 20 500 10 700 6000 50000 50 800 300
## [21] 9000 30000 8000 70 10000 40 30 80 20000 60
## [31] 90 200000 7000 2 7 100000 3 6
range(dt5$Weight) #2-200000
## [1] 2 200000
# Income Categories:
dt5_sub1 <- subset(dt5, dt5$Source >= 500000) # Subset of data with only income categories
str(dt5_sub1)
## 'data.frame': 114 obs. of 5 variables:
## $ Source: chr "620120" "620120" "620120" "620120" ...
## $ eType : int 5 5 5 5 5 5 5 5 5 5 ...
## $ Target: chr "36" "37" "38" "40" ...
## $ Time : int 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 ...
## $ Weight: int 700 800 400 300 7000 2000 200000 50 300 600 ...
plot(dt5_sub1$Source, dt5_sub1$Weight) # Plot of Monetary income in each category
# Expense Categories:
dt5_sub2 <- subset(dt5, dt5$Target >= 500000) # Subset of data with only expense categories
str(dt5_sub2)
## 'data.frame': 180 obs. of 5 variables:
## $ Source: chr "2" "2" "2" "2" ...
## $ eType : int 5 5 5 5 5 5 5 5 5 5 ...
## $ Target: chr "630626" "642329" "644226" "632961" ...
## $ Time : int 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 ...
## $ Weight: int 5000 1000 500 10 5000 700 6000 800 2000 800 ...
plot(dt5_sub2$Target, dt5_sub2$Weight) # Plot of Monetary expenses in each category
#any(dt6$Source) == any(dt6$Target)
Graph 1 Analysis:
qt1 <- data.table::fread(here::here("data", "Q1-Graph1.csv"))
head(qt1)
## Source eType Target Time Weight SourceLocation TargetLocation
## 1: 616050 4 590502 -662041253 0.166667 NA NA
## 2: 599956 0 635665 1296000 1.000000 NA NA
## 3: 599956 0 490041 1306507 1.000000 NA NA
## 4: 599956 0 490041 1312679 1.000000 NA NA
## 5: 490041 0 599956 1314435 1.000000 NA NA
## 6: 490041 0 599956 1331859 1.000000 NA NA
## SourceLatitude SourceLongitude TargetLatitude TargetLongitude
## 1: NA NA NA NA
## 2: NA NA NA NA
## 3: NA NA NA NA
## 4: NA NA NA NA
## 5: NA NA NA NA
## 6: NA NA NA NA
tail(qt1)
## Source eType Target Time Weight SourceLocation TargetLocation
## 1: 533140 5 642329 31536000 1131.24 NA NA
## 2: 533140 5 503701 31536000 1741.49 NA NA
## 3: 533140 5 571970 31536000 85.16 NA NA
## 4: 533140 5 632961 31536000 290.73 NA NA
## 5: 533140 5 473173 31536000 1516.94 NA NA
## 6: 533140 5 620120 31536000 333.78 NA NA
## SourceLatitude SourceLongitude TargetLatitude TargetLongitude
## 1: NA NA NA NA
## 2: NA NA NA NA
## 3: NA NA NA NA
## 4: NA NA NA NA
## 5: NA NA NA NA
## 6: NA NA NA NA
# Summarising the Data:
summary(qt1)
## Source eType Target Time
## Min. :463777 Min. :0.000 Min. :459381 Min. :-662041253
## 1st Qu.:512397 1st Qu.:1.000 1st Qu.:523927 1st Qu.: 22838456
## Median :570411 Median :5.000 Median :577992 Median : 31536000
## Mean :566372 Mean :3.801 Mean :566666 Mean : 25825976
## 3rd Qu.:616050 3rd Qu.:5.000 3rd Qu.:620120 3rd Qu.: 31536000
## Max. :654981 Max. :6.000 Max. :657187 Max. : 31536000
##
## Weight SourceLocation TargetLocation SourceLatitude
## Min. : 0.2 Min. :0.000 Min. :0.000 Min. :-29.000
## 1st Qu.: 1.0 1st Qu.:0.000 1st Qu.:0.000 1st Qu.:-24.566
## Median : 655.2 Median :0.000 Median :2.000 Median : 27.203
## Mean : 5441.3 Mean :1.321 Mean :1.363 Mean : 6.367
## 3rd Qu.: 2474.7 3rd Qu.:3.000 3rd Qu.:2.000 3rd Qu.: 34.296
## Max. :900735.0 Max. :5.000 Max. :5.000 Max. : 35.881
## NA's :1048 NA's :1048 NA's :1048
## SourceLongitude TargetLatitude TargetLongitude
## Min. :-165.00 Min. :-29.000 Min. :-165.00
## 1st Qu.:-110.65 1st Qu.:-22.000 1st Qu.: -48.67
## Median : -39.03 Median : 1.000 Median : -37.81
## Mean : -31.99 Mean : 4.171 Mean : -17.57
## 3rd Qu.: -34.54 3rd Qu.: 30.448 3rd Qu.: 89.42
## Max. : 156.00 Max. : 35.881 Max. : 156.00
## NA's :1048 NA's :1048 NA's :1048
nrow(qt1) #1216
## [1] 1216
ncol(qt1) #11
## [1] 11
qt1$Source <- as.character(qt1$Source)
qt1$Target <- as.character(qt1$Target)
# Differentiating between channels:
qt1_01 <- qt1 %>% filter(qt1$eType == 0 | qt1$eType == 1) # Communication Channel
nrow(qt1_01) # 318
## [1] 318
qt1_23 <- qt1 %>% filter(qt1$eType == 2 | qt1$eType == 3) # Procurement Channel
nrow(qt1_23) # 14
## [1] 14
qt1_4 <- qt1 %>% filter(qt1$eType == 4) # Co-authorship Channel
nrow(qt1_4) # 1
## [1] 1
qt1_5 <- qt1 %>% filter(qt1$eType == 5) # Demographic Channel
nrow(qt1_5) # 846
## [1] 846
qt1_6 <- qt1 %>% filter(qt1$eType == 6) # Travel Channel
nrow(qt1_6) # 37
## [1] 37
# Highest data for Demographic, Communication and Travel Channel.
# Analysis of the Communication channel:
glimpse(qt1_01)
## Observations: 318
## Variables: 11
## $ Source <chr> "599956", "599956", "599956", "490041", "49004...
## $ eType <int> 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 1, 1, 1, 0...
## $ Target <chr> "635665", "490041", "490041", "599956", "59995...
## $ Time <int> 1296000, 1306507, 1312679, 1314435, 1331859, 1...
## $ Weight <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1...
## $ SourceLocation <int> NA, NA, NA, NA, NA, NA, NA, NA, 0, 0, NA, 0, 0...
## $ TargetLocation <int> NA, NA, NA, NA, NA, NA, NA, NA, 0, 0, NA, 0, 0...
## $ SourceLatitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, 34.5741, 34.29...
## $ SourceLongitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, -42.0541, -39....
## $ TargetLatitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, 30.4483, 29.32...
## $ TargetLongitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, -42.5341, -37....
#unique(qt1_01)
unique(qt1_01$eType) # 0 1
## [1] 0 1
unique(qt1_01$SourceLocation) # NA 0 2 3
## [1] NA 0 2 3
unique(qt1_01$TargetLocation) # NA 0 2 3
## [1] NA 0 2 3
unique(qt1_01$SourceLatitude) # NA 34.5741 34.2958 -27.2563 29.3296 -20.9062 -21.8004 25.0754 -25.4639 -24.5657 -18.3758 30.4483 35.8806
## [1] NA 34.5741 34.2958 -27.2563 29.3296 -20.9062 -21.8004
## [8] 25.0754 -25.4639 -24.5657 -18.3758 30.4483 35.8806
unique(qt1_01$SourceLongitude) # NA -42.0541 -39.0260 91.7676 -37.8076 92.3982 89.7045 -40.6293 -111.2490 -110.6500 91.0250 -42.5341 -34.5372
## [1] NA -42.0541 -39.0260 91.7676 -37.8076 92.3982 89.7045
## [8] -40.6293 -111.2490 -110.6500 91.0250 -42.5341 -34.5372
unique(qt1_01$TargetLatitude) # NA 30.4483 29.3296 34.2958 34.5741 28.3004 -27.2563 -22.6503 -21.8004 -20.9062 25.0754 -24.5657 -20.8686 -18.3758
## [1] NA 30.4483 29.3296 34.2958 34.5741 28.3004 -27.2563
## [8] -22.6503 -21.8004 -20.9062 25.0754 -24.5657 -20.8686 -18.3758
## [15] 32.6654 -25.4639 -17.1099 35.8806
# 32.6654 -25.4639 -17.1099 35.8806
unique(qt1_01$TargetLongitude) # NA -42.5341 -37.8076 -39.0260 -42.0541 -47.4036 91.7676 92.6106 89.7045 92.3982 -40.6293 -110.6500 89.4217
## [1] NA -42.5341 -37.8076 -39.0260 -42.0541 -47.4036 91.7676
## [8] 92.6106 89.7045 92.3982 -40.6293 -110.6500 89.4217 91.0250
## [15] -48.6701 -111.2490 90.7971 -34.5372
#91.0250 -48.6701 -111.2490 90.7971 -34.5372
unique(qt1_01$Source) # 599956 490041 533140 568093 632150 635665 616050 512397 623295 589639 550287 550361 596193
## [1] "599956" "490041" "533140" "568093" "632150" "635665" "616050"
## [8] "512397" "623295" "589639" "550287" "550361" "596193" "464459"
## [15] "492777" "570411" "640464"
# 464459 492777 570411 640464
unique(qt1_01$Target) # 635665 490041 599956 589639 591682 616050 568093 632150 464459 533140 512397 550287 559657
## [1] "635665" "490041" "599956" "589639" "591682" "616050" "568093"
## [8] "632150" "464459" "533140" "512397" "550287" "559657" "492777"
## [15] "570411" "493044" "596193" "550361" "640464" "623295"
# 492777 570411 493044 596193 550361 640464 623295
colnames(qt1_01)
## [1] "Source" "eType" "Target"
## [4] "Time" "Weight" "SourceLocation"
## [7] "TargetLocation" "SourceLatitude" "SourceLongitude"
## [10] "TargetLatitude" "TargetLongitude"
# Analysis of the Demographic channel:
glimpse(qt1_5)
## Observations: 846
## Variables: 11
## $ Source <chr> "608827", "552988", "608827", "608827", "60882...
## $ eType <int> 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5...
## $ Target <chr> "630626", "608827", "567195", "527449", "45938...
## $ Time <int> 31536000, 31536000, 31536000, 31536000, 315360...
## $ Weight <dbl> 21699.30, 143858.00, 15088.40, 456.71, 2378.60...
## $ SourceLocation <int> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLocation <int> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ SourceLatitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ SourceLongitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLatitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLongitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
#unique(qt1_5)
unique(qt1_5$eType) # 5
## [1] 5
unique(qt1_5$SourceLocation) # NA
## [1] NA
unique(qt1_5$TargetLocation) # NA
## [1] NA
unique(qt1_5$SourceLatitude) # NA
## [1] NA
unique(qt1_5$SourceLongitude) # NA
## [1] NA
unique(qt1_5$TargetLatitude) # NA
## [1] NA
unique(qt1_5$TargetLongitude) # NA
## [1] NA
unique(qt1_5$Source)
## [1] "608827" "552988" "589639" "510031" "530528" "635706" "490041"
## [8] "554431" "620120" "599956" "566342" "548513" "599057" "568093"
## [15] "464459" "635665" "474199" "475130" "596193" "576641" "550361"
## [22] "463777" "654763" "529922" "599063" "622296" "512397" "493044"
## [29] "592414" "575704" "654981" "575859" "640464" "505722" "517273"
## [36] "492286" "636961" "570411" "623295" "492777" "629717" "502591"
## [43] "569820" "591682" "632150" "616050" "533140"
unique(qt1_5$Target)
## [1] "630626" "608827" "567195" "527449" "459381" "595298" "466907"
## [8] "589943" "537281" "580426" "595581" "616315" "642329" "503701"
## [15] "632961" "473173" "620120" "575030" "621924" "536346" "589639"
## [22] "520660" "577992" "571970" "644226" "530528" "523927" "635706"
## [29] "490041" "554431" "599956" "566342" "548513" "599057" "568093"
## [36] "464459" "640784" "635665" "474199" "475130" "596193" "576641"
## [43] "550361" "463777" "503218" "654763" "529922" "599063" "606730"
## [50] "622296" "512397" "493044" "592414" "575704" "654981" "575859"
## [57] "640464" "505722" "517273" "492286" "636961" "570411" "623295"
## [64] "492777" "629717" "502591" "569820" "591682" "632150" "616050"
## [71] "533140"
unique(qt1_5$Weight)
## [1] 21699.30 143858.00 15088.40 456.71 2378.60 5362.15 1689.16
## [8] 8444.03 2111.52 385.87 1006.36 6192.98 6393.29 2935.06
## [15] 116.31 4951.15 19480.80 14153.40 12677.50 25079.40 9368.15
## [22] 1840.81 12000.00 647030.00 35981.50 1570.79 1177.72 6259.14
## [29] 4315.51 17326.80 59222.40 6812.65 7992.34 10936.90 11748.40
## [36] 922.08 4393.27 657.25 256705.00 22255.40 20611.70 8433.51
## [43] 42.39 1273.93 10454.00 22471.70 3256.84 626.25 709.74
## [50] 323.75 803.27 5401.11 566.66 1055.24 1263.37 1860.01
## [57] 1056.28 572.39 2654.76 1258.56 2025.14 3136.11 32074.00
## [64] 23825.60 619963.00 19509.30 707.75 2812.20 1346.38 1827.44
## [71] 8451.08 179.25 6537.83 7422.71 5502.61 419.71 1568.36
## [78] 288399.00 12879.00 3877.78 3898.00 3164.62 9945.27 3425.74
## [85] 190.90 944.51 2351.23 3472.76 2016.75 5981.19 541.23
## [92] 2715.88 1124.28 755.36 1088.30 1277.89 546.79 902.70
## [99] 989.20 309.48 8432.04 2533.31 25798.30 4869.66 477.21
## [106] 991.31 1022.79 1592.45 2292.69 575.81 2100.87 507.66
## [113] 864.50 3608.19 11532.20 109.57 2609.97 1916.13 8023.05
## [120] 4588.96 15128.20 2378.96 4527.75 11521.20 87411.80 14199.50
## [127] 1287.62 1200.80 5424.06 1734.92 4308.22 573.69 3138.12
## [134] 2612.14 4236.90 5658.37 801.56 3394.47 6039.55 33836.20
## [141] 4397.31 2836.39 11191.50 239.28 928.67 2976.70 1503.23
## [148] 1392.07 1673.49 729.47 695.41 2325.96 3830.14 409.84
## [155] 730.67 350.38 201.24 4154.76 1246.31 5458.02 3302.11
## [162] 1688.22 7279.05 8328.29 3345.40 706.38 2555.54 6392.63
## [169] 1499.50 479.26 4817.44 60.39 1464.26 1129.58 1057.83
## [176] 989.89 11194.70 937.43 1282.76 1584.35 26766.30 4545.13
## [183] 50.84 1671.82 151.14 607.33 2235.21 121.90 1013.67
## [190] 1123.79 2716.78 7222.34 2032.53 147.47 5174.10 2317.44
## [197] 3217.81 10786.00 423.63 1351.29 6929.54 462.80 2057.60
## [204] 5152.55 276.35 3047.35 4470.49 1230.07 55.90 1626.36
## [211] 2087.31 1770.99 453.32 51492.70 1167.72 534.04 1702.60
## [218] 2991.42 1601.52 3184.21 1845.19 1784.67 4296.71 3261.55
## [225] 763.63 699.42 1690.82 3442.81 6587.65 5937.72 197.19
## [232] 1388.78 30019.90 2739.08 39.34 1448.59 4378.48 3826.62
## [239] 377.01 698.17 1576.24 5382.42 896.83 4052.61 5472.26
## [246] 34041.90 461.46 556.31 7508.97 195.80 619.57 199.86
## [253] 900.45 1383.94 134.40 101.17 739.24 314.86 229.05
## [260] 134.02 826.39 500.51 3106.61 1288.30 10098.50 296.73
## [267] 464.59 760.17 750.34 2085.70 48.06 227.90 873.60
## [274] 606.11 923.51 691.64 233.20 1402.55 32.31 136.86
## [281] 1083.35 598.50 7055.78 25.88 498.56 3494.46 215.51
## [288] 5715.91 80.41 114.24 762.62 3200.76 5.50 505.63
## [295] 512.20 1413.95 740.74 5373.20 2326.88 101.93 57.70
## [302] 385.35 1277.17 607.00 564.31 276.28 496.73 480.73
## [309] 878.76 1617.76 62.22 349.80 532.92 367.71 2681.86
## [316] 1078.75 12586.90 2912.89 114.69 235.50 1135.49 2474.91
## [323] 489.54 94.05 382.99 820.04 201.32 1870.79 152.14
## [330] 1378.84 333.88 94.43 3691.55 626.00 583.52 763.66
## [337] 226.36 1823.50 7392.60 851.71 193.02 436.80 1409.48
## [344] 208.84 427.55 4864.11 474.25 1561.97 316.86 693.07
## [351] 1471.99 1690.67 205.66 73.59 522.83 168.12 2870.09
## [358] 4575.82 566.76 4412.63 999.02 22959.00 1941.65 399.58
## [365] 613.32 3795.32 511.93 2217.83 1069.28 169.61 1643.03
## [372] 50.58 1933.55 431.16 81.33 319.93 568.90 1537.07
## [379] 6042.72 561.90 1056.71 47106.50 889.15 233.11 388.16
## [386] 2032.07 512.78 3011.76 920.72 690.54 481.91 2047.56
## [393] 1647.79 220.36 3689.19 119.01 1072.89 390.31 1715.33
## [400] 7263.71 9216.46 1790.27 2267.03 1307.49 75.86 2061.29
## [407] 19798.90 960.36 54.66 414.66 2085.13 1092.76 1526.12
## [414] 554.65 1346.45 1443.58 581.21 3459.56 2836.08 2708.54
## [421] 3118.43 746.42 5301.05 942.41 3331.50 36123.40 2796.56
## [428] 170.12 667.40 567.63 554.54 2927.57 750.85 2215.35
## [435] 1981.13 2446.33 164.15 623.17 229.10 347.59 4579.47
## [442] 965.86 19.92 1119.13 6106.78 881.23 4200.84 32518.90
## [449] 4880.51 343.32 993.54 2840.81 711.50 1254.79 739.49
## [456] 732.21 3252.44 6308.05 321.43 1180.66 22.79 1984.33
## [463] 913.17 4962.24 4388.86 11068.60 2487.82 5087.50 1472.52
## [470] 822.40 18919.40 1684.01 377.60 224.81 1684.21 658.91
## [477] 1094.45 75.77 130.79 1412.76 125.63 2554.09 1702.58
## [484] 45.08 1858.42 774.25 7441.46 1167.94 49976.20 5063.82
## [491] 576.89 1265.29 3137.79 1107.68 5302.38 1441.09 720.36
## [498] 4573.48 483.10 2658.66 3429.01 1882.53 2522.31 243.81
## [505] 725.17 5471.99 596.72 31934.90 749.74 2391.69 4273.66
## [512] 196.03 9784.56 1557.66 1911.13 693.04 4613.15 2660.68
## [519] 849.79 3479.68 2255.94 304.79 10753.80 1787.56 558.05
## [526] 1805.45 1269.47 655.88 5306.54 244.20 2434.08 386.83
## [533] 986.55 586.73 499.85 620.87 732.43 2151.07 1267.83
## [540] 3304.77 477.89 132.10 766.88 366.20 1168.58 2274.47
## [547] 976.38 779.37 2474.64 183.40 440.95 1543.60 9070.65
## [554] 1296.75 1163.10 6292.61 3406.61 493.08 2318.11 5720.56
## [561] 1136.42 162.29 7905.27 20.21 899.28 129.52 1315.33
## [568] 4161.23 426.58 422.50 1259.00 1089.87 3780.69 4118.47
## [575] 34840.30 7190.11 900735.00 62750.40 238.75 1721.87 6060.91
## [582] 4593.29 20056.80 1137.66 3425.98 11587.20 14641.30 11493.80
## [589] 12163.60 8086.96 9231.82 9236.96 18476.70 3161.42 121149.00
## [596] 461.18 1589.03 18128.60 3709.53 6858.84 8669.64 1775.55
## [603] 286.56 8511.84 5037.65 3021.52 5355.92 436.23 2229.71
## [610] 1112.61 20241.90 14630.50 1370.28 12542.50 69256.80 14538.30
## [617] 883.83 1166.80 2904.37 1376.82 598.14 5422.26 5061.07
## [624] 7666.80 905.48 4242.92 260.88 1609.83 794.47 15251.00
## [631] 39657.70 72.49 1323.60 3939.83 5807.39 2846.66 884.99
## [638] 2423.74 375.30 587.83 0.46 450.03 274.65 3215.16
## [645] 76.17 917.55 5236.45 2976.51 559.30 410.44 3209.39
## [652] 2524.68 15868.40 5580.80 209.30 5688.59 76722.10 17179.00
## [659] 574.26 1991.54 2665.72 690.53 1689.51 1317.79 3426.73
## [666] 2200.13 578.66 4046.65 985.43 12330.70 5599.51 2276.97
## [673] 467.09 11546.50 699.55 182.71 216.96 785.52 656.77
## [680] 1949.02 325.56 691.26 1906.60 802.67 1189.79 1553.68
## [687] 1131.20 1099.51 2838.79 9732.82 1073.08 124.26 360.75
## [694] 611.56 128.47 1598.66 185.63 535.22 815.28 1619.79
## [701] 146.65 147.32 1461.98 947.58 6491.57 1518.45 4249.15
## [708] 1091.21 21204.90 2015.43 73.20 889.20 2575.65 312.96
## [715] 2726.24 1563.82 654.51 245.42 2484.21 192.93 1856.92
## [722] 281.98 478.91 843.46 4168.46 296.54 4144.78 1101.40
## [729] 525.02 4874.08 54333.10 536.87 768.82 382.45 4093.29
## [736] 631.99 1369.20 1399.54 266.52 2099.77 2810.98 5503.51
## [743] 218.21 814.80 488.63 669.18 9247.45 2572.76 273.24
## [750] 8464.39 1702.37 202871.00 2942.39 87.40 629.72 3574.60
## [757] 808.95 534.52 5383.92 647.27 3093.55 2682.75 2875.99
## [764] 1345.06 3718.44 604.29 1512.55 97.31 73919.00 7133.86
## [771] 6704.79 1502.74 5662.73 678.13 986.71 25608.40 218.03
## [778] 622.49 3245.92 946.77 1180.70 712.92 2053.41 220.80
## [785] 2019.74 943.81 599.59 1694.31 806.75 2644.97 6090.91
## [792] 4091.49 137.73 4811.33 489.09 28528.20 303.25 790.06
## [799] 1224.30 658.42 2231.39 1608.67 915.47 1996.20 1118.52
## [806] 822.59 1302.15 3720.79 803.32 6218.94 540.85 637.05
## [813] 43606.40 9865.87 142.08 510.26 3407.94 824.91 2521.46
## [820] 1136.81 4913.07 2707.57 1036.27 360.95 821.76 8076.13
## [827] 7832.08 1670.72 3150.22 235.04 14701.40 534.56 96.46
## [834] 279.66 1314.31 507.01 530.60 497.08 239.94 1131.24
## [841] 1741.49 85.16 290.73 1516.94 333.78
qt1_5 <- subset(qt1_5, select = -c(SourceLocation, TargetLocation, SourceLatitude, SourceLongitude, TargetLatitude, TargetLongitude)) # SOurce and Target Latitude and Longitude columns removed as all Null.
colnames(qt1_5)
## [1] "Source" "eType" "Target" "Time" "Weight"
range(qt1_5$Source) # 463777-654981
## [1] "463777" "654981"
range(qt1_5$Target) # 459381-654981
## [1] "459381" "654981"
range(qt1_5$Time) # 31536000-31536000
## [1] 31536000 31536000
income_cat_qt1 <- NULL
# Income Categories:
for (i in (qt1_5$Source)) {
for (j in (cat$NodeID)) { # cat_list contains all the demographic nodeIDs (from the DemographicNodeExtraction Script)
if(i == j){
income_cat_qt1 <- append(income_cat_qt1,i)
}
}
}
print(income_cat_qt1) # income categories extracted
## [1] "552988" "510031" "552988" "510031" "552988" "510031" "552988"
## [8] "552988" "510031" "552988" "620120" "510031" "552988" "552988"
## [15] "510031" "552988" "620120" "510031" "552988" "620120" "552988"
## [22] "510031" "552988" "620120" "510031" "552988" "510031" "552988"
## [29] "620120" "510031" "552988" "552988" "552988" "552988" "510031"
## [36] "552988" "620120" "510031" "552988" "552988" "510031" "552988"
## [43] "552988" "552988" "552988" "552988" "620120" "510031" "552988"
## [50] "510031" "552988" "510031" "552988" "510031" "552988" "620120"
## [57] "510031" "552988" "510031" "552988" "552988" "552988" "620120"
## [64] "510031" "552988" "510031" "552988" "552988" "620120" "510031"
## [71] "552988" "510031" "552988" "510031" "552988" "552988" "510031"
## [78] "552988" "510031" "552988" "510031" "552988"
unique(income_cat_qt1) # 3
## [1] "552988" "510031" "620120"
qt1_5_sub1 <- subset(qt1_5, qt1_5$Source == income_cat_qt1) # Subset of data with only income categories
## Warning in qt1_5$Source == income_cat_qt1: longer object length is not a
## multiple of shorter object length
str(qt1_5_sub1)
## 'data.frame': 38 obs. of 5 variables:
## $ Source: chr "510031" "552988" "510031" "552988" ...
## $ eType : int 5 5 5 5 5 5 5 5 5 5 ...
## $ Target: chr "589639" "530528" "635706" "635706" ...
## $ Time : int 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 ...
## $ Weight: num 1841 22472 23826 619963 9945 ...
plot(qt1_5_sub1$Source, qt1_5_sub1$Weight) # Plot of Monetary income in each category
# Expense Categories:
expense_cat_qt1 <- 0
for (k in qt1_5$Target) {
for(l in cat$NodeID){
if(k==l){
expense_cat_qt1 <- append(expense_cat_qt1, k)
}
}
}
print(expense_cat_qt1) # expense categories extracted
## [1] "0" "630626" "567195" "527449" "459381" "595298" "466907"
## [8] "589943" "537281" "580426" "595581" "616315" "642329" "503701"
## [15] "632961" "473173" "620120" "575030" "621924" "630626" "536346"
## [22] "520660" "567195" "527449" "459381" "595298" "466907" "589943"
## [29] "577992" "595581" "616315" "642329" "503701" "571970" "644226"
## [36] "473173" "620120" "575030" "621924" "630626" "536346" "520660"
## [43] "567195" "527449" "459381" "595298" "466907" "577992" "523927"
## [50] "580426" "616315" "642329" "503701" "571970" "644226" "632961"
## [57] "473173" "620120" "630626" "567195" "527449" "459381" "595298"
## [64] "466907" "589943" "537281" "580426" "642329" "503701" "571970"
## [71] "473173" "620120" "575030" "630626" "536346" "520660" "567195"
## [78] "527449" "459381" "595298" "589943" "537281" "523927" "616315"
## [85] "642329" "503701" "571970" "644226" "632961" "473173" "620120"
## [92] "575030" "621924" "630626" "567195" "527449" "459381" "595298"
## [99] "466907" "589943" "537281" "523927" "580426" "595581" "642329"
## [106] "503701" "571970" "473173" "575030" "621924" "630626" "536346"
## [113] "520660" "567195" "527449" "459381" "595298" "466907" "589943"
## [120] "577992" "537281" "523927" "642329" "503701" "644226" "473173"
## [127] "620120" "575030" "621924" "630626" "527449" "459381" "595298"
## [134] "466907" "589943" "577992" "537281" "523927" "616315" "642329"
## [141] "571970" "632961" "473173" "620120" "575030" "621924" "630626"
## [148] "536346" "520660" "567195" "527449" "459381" "595298" "589943"
## [155] "580426" "595581" "571970" "644226" "473173" "621924" "630626"
## [162] "536346" "520660" "567195" "527449" "459381" "595298" "466907"
## [169] "589943" "577992" "523927" "595581" "616315" "503701" "644226"
## [176] "632961" "473173" "621924" "527449" "459381" "595298" "466907"
## [183] "589943" "577992" "580426" "595581" "616315" "503701" "632961"
## [190] "473173" "620120" "621924" "567195" "527449" "459381" "595298"
## [197] "466907" "577992" "537281" "523927" "595581" "616315" "571970"
## [204] "632961" "473173" "575030" "621924" "640784" "567195" "527449"
## [211] "459381" "595298" "577992" "537281" "580426" "642329" "503701"
## [218] "632961" "473173" "620120" "575030" "621924" "567195" "527449"
## [225] "459381" "595298" "589943" "577992" "537281" "580426" "595581"
## [232] "642329" "571970" "473173" "575030" "527449" "459381" "595298"
## [239] "466907" "589943" "577992" "537281" "523927" "580426" "595581"
## [246] "616315" "642329" "503701" "571970" "632961" "473173" "620120"
## [253] "527449" "459381" "595298" "466907" "577992" "523927" "580426"
## [260] "642329" "503701" "571970" "632961" "473173" "620120" "575030"
## [267] "621924" "567195" "527449" "459381" "595298" "466907" "589943"
## [274] "537281" "523927" "580426" "595581" "503701" "571970" "473173"
## [281] "620120" "575030" "630626" "536346" "567195" "527449" "459381"
## [288] "595298" "589943" "537281" "523927" "580426" "595581" "642329"
## [295] "503701" "571970" "644226" "473173" "620120" "575030" "621924"
## [302] "630626" "536346" "520660" "567195" "527449" "459381" "595298"
## [309] "466907" "589943" "577992" "537281" "523927" "580426" "595581"
## [316] "616315" "503701" "644226" "632961" "473173" "575030" "621924"
## [323] "503218" "630626" "567195" "527449" "459381" "595298" "466907"
## [330] "589943" "537281" "580426" "595581" "642329" "503701" "632961"
## [337] "473173" "620120" "575030" "621924" "630626" "536346" "520660"
## [344] "567195" "527449" "459381" "595298" "466907" "589943" "577992"
## [351] "523927" "580426" "595581" "616315" "642329" "503701" "571970"
## [358] "644226" "632961" "473173" "620120" "575030" "621924" "630626"
## [365] "536346" "520660" "567195" "527449" "459381" "595298" "606730"
## [372] "589943" "577992" "523927" "616315" "642329" "503701" "644226"
## [379] "632961" "473173" "620120" "621924" "630626" "536346" "520660"
## [386] "567195" "527449" "459381" "595298" "466907" "589943" "577992"
## [393] "595581" "616315" "503701" "571970" "644226" "632961" "473173"
## [400] "620120" "575030" "621924" "640784" "630626" "536346" "520660"
## [407] "567195" "527449" "459381" "595298" "466907" "606730" "577992"
## [414] "537281" "523927" "595581" "616315" "642329" "571970" "644226"
## [421] "632961" "473173" "620120" "575030" "621924" "630626" "536346"
## [428] "520660" "567195" "527449" "459381" "595298" "466907" "537281"
## [435] "523927" "580426" "595581" "642329" "503701" "644226" "632961"
## [442] "473173" "620120" "575030" "621924" "567195" "527449" "459381"
## [449] "595298" "466907" "589943" "577992" "537281" "523927" "580426"
## [456] "595581" "616315" "642329" "503701" "571970" "473173" "527449"
## [463] "459381" "595298" "606730" "589943" "537281" "523927" "580426"
## [470] "595581" "503701" "632961" "473173" "620120" "567195" "527449"
## [477] "459381" "595298" "466907" "577992" "537281" "523927" "580426"
## [484] "595581" "503701" "571970" "632961" "473173" "620120" "567195"
## [491] "527449" "459381" "595298" "589943" "537281" "523927" "580426"
## [498] "595581" "503701" "473173" "620120" "575030" "621924" "567195"
## [505] "527449" "459381" "595298" "466907" "589943" "577992" "537281"
## [512] "523927" "580426" "595581" "616315" "571970" "632961" "473173"
## [519] "621924" "503218" "630626" "567195" "527449" "459381" "595298"
## [526] "466907" "589943" "537281" "580426" "595581" "616315" "642329"
## [533] "503701" "473173" "620120" "621924" "630626" "527449" "459381"
## [540] "595298" "466907" "589943" "577992" "523927" "580426" "595581"
## [547] "616315" "642329" "503701" "571970" "632961" "473173" "620120"
## [554] "575030" "621924" "630626" "567195" "527449" "459381" "595298"
## [561] "466907" "537281" "523927" "595581" "616315" "642329" "503701"
## [568] "571970" "632961" "473173" "620120" "575030" "621924" "503218"
## [575] "630626" "567195" "527449" "459381" "595298" "466907" "589943"
## [582] "577992" "537281" "523927" "580426" "595581" "642329" "503701"
## [589] "571970" "473173" "621924" "630626" "536346" "520660" "567195"
## [596] "527449" "459381" "595298" "466907" "577992" "580426" "595581"
## [603] "503701" "571970" "644226" "473173" "620120" "575030" "621924"
## [610] "567195" "527449" "459381" "595298" "466907" "589943" "577992"
## [617] "537281" "523927" "595581" "503701" "473173" "620120" "621924"
## [624] "630626" "567195" "527449" "459381" "595298" "466907" "589943"
## [631] "580426" "616315" "642329" "503701" "571970" "632961" "473173"
## [638] "575030" "621924" "630626" "567195" "527449" "459381" "595298"
## [645] "466907" "589943" "577992" "523927" "580426" "616315" "642329"
## [652] "503701" "632961" "473173" "620120" "575030" "621924" "630626"
## [659] "536346" "520660" "567195" "527449" "459381" "595298" "466907"
## [666] "577992" "537281" "523927" "595581" "616315" "503701" "571970"
## [673] "644226" "632961" "473173" "620120" "621924" "640784" "630626"
## [680] "567195" "527449" "459381" "595298" "466907" "606730" "589943"
## [687] "537281" "523927" "580426" "595581" "642329" "503701" "571970"
## [694] "632961" "473173" "620120" "575030" "621924" "640784" "630626"
## [701] "536346" "520660" "527449" "459381" "595298" "466907" "589943"
## [708] "537281" "523927" "580426" "595581" "616315" "642329" "644226"
## [715] "632961" "473173" "620120" "575030" "621924" "630626" "527449"
## [722] "459381" "595298" "466907" "589943" "523927" "580426" "595581"
## [729] "616315" "503701" "473173" "620120" "621924" "630626" "536346"
## [736] "567195" "527449" "459381" "595298" "466907" "589943" "523927"
## [743] "595581" "503701" "644226" "632961" "473173" "620120" "575030"
## [750] "621924" "630626" "567195" "527449" "459381" "595298" "466907"
## [757] "577992" "537281" "616315" "642329" "503701" "571970" "632961"
## [764] "473173" "620120"
unique(expense_cat_qt1) # 27
## [1] "0" "630626" "567195" "527449" "459381" "595298" "466907"
## [8] "589943" "537281" "580426" "595581" "616315" "642329" "503701"
## [15] "632961" "473173" "620120" "575030" "621924" "536346" "520660"
## [22] "577992" "571970" "644226" "523927" "640784" "503218" "606730"
qt1_5_sub2 <- subset(qt1_5, qt1_5$Target == expense_cat_qt1) # Subset of data with only expense categories
## Warning in qt1_5$Target == expense_cat_qt1: longer object length is not a
## multiple of shorter object length
str(qt1_5_sub2)
## 'data.frame': 43 obs. of 5 variables:
## $ Source: chr "608827" "608827" "608827" "608827" ...
## $ eType : int 5 5 5 5 5 5 5 5 5 5 ...
## $ Target: chr "567195" "527449" "459381" "595298" ...
## $ Time : int 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 ...
## $ Weight: num 15088 457 2379 5362 1689 ...
plot(qt1_5_sub2$Target, qt1_5_sub2$Weight) # Plot of Monetary expenses in each category
hist(qt1_5$Weight)
unique(qt1_5$Weight)
## [1] 21699.30 143858.00 15088.40 456.71 2378.60 5362.15 1689.16
## [8] 8444.03 2111.52 385.87 1006.36 6192.98 6393.29 2935.06
## [15] 116.31 4951.15 19480.80 14153.40 12677.50 25079.40 9368.15
## [22] 1840.81 12000.00 647030.00 35981.50 1570.79 1177.72 6259.14
## [29] 4315.51 17326.80 59222.40 6812.65 7992.34 10936.90 11748.40
## [36] 922.08 4393.27 657.25 256705.00 22255.40 20611.70 8433.51
## [43] 42.39 1273.93 10454.00 22471.70 3256.84 626.25 709.74
## [50] 323.75 803.27 5401.11 566.66 1055.24 1263.37 1860.01
## [57] 1056.28 572.39 2654.76 1258.56 2025.14 3136.11 32074.00
## [64] 23825.60 619963.00 19509.30 707.75 2812.20 1346.38 1827.44
## [71] 8451.08 179.25 6537.83 7422.71 5502.61 419.71 1568.36
## [78] 288399.00 12879.00 3877.78 3898.00 3164.62 9945.27 3425.74
## [85] 190.90 944.51 2351.23 3472.76 2016.75 5981.19 541.23
## [92] 2715.88 1124.28 755.36 1088.30 1277.89 546.79 902.70
## [99] 989.20 309.48 8432.04 2533.31 25798.30 4869.66 477.21
## [106] 991.31 1022.79 1592.45 2292.69 575.81 2100.87 507.66
## [113] 864.50 3608.19 11532.20 109.57 2609.97 1916.13 8023.05
## [120] 4588.96 15128.20 2378.96 4527.75 11521.20 87411.80 14199.50
## [127] 1287.62 1200.80 5424.06 1734.92 4308.22 573.69 3138.12
## [134] 2612.14 4236.90 5658.37 801.56 3394.47 6039.55 33836.20
## [141] 4397.31 2836.39 11191.50 239.28 928.67 2976.70 1503.23
## [148] 1392.07 1673.49 729.47 695.41 2325.96 3830.14 409.84
## [155] 730.67 350.38 201.24 4154.76 1246.31 5458.02 3302.11
## [162] 1688.22 7279.05 8328.29 3345.40 706.38 2555.54 6392.63
## [169] 1499.50 479.26 4817.44 60.39 1464.26 1129.58 1057.83
## [176] 989.89 11194.70 937.43 1282.76 1584.35 26766.30 4545.13
## [183] 50.84 1671.82 151.14 607.33 2235.21 121.90 1013.67
## [190] 1123.79 2716.78 7222.34 2032.53 147.47 5174.10 2317.44
## [197] 3217.81 10786.00 423.63 1351.29 6929.54 462.80 2057.60
## [204] 5152.55 276.35 3047.35 4470.49 1230.07 55.90 1626.36
## [211] 2087.31 1770.99 453.32 51492.70 1167.72 534.04 1702.60
## [218] 2991.42 1601.52 3184.21 1845.19 1784.67 4296.71 3261.55
## [225] 763.63 699.42 1690.82 3442.81 6587.65 5937.72 197.19
## [232] 1388.78 30019.90 2739.08 39.34 1448.59 4378.48 3826.62
## [239] 377.01 698.17 1576.24 5382.42 896.83 4052.61 5472.26
## [246] 34041.90 461.46 556.31 7508.97 195.80 619.57 199.86
## [253] 900.45 1383.94 134.40 101.17 739.24 314.86 229.05
## [260] 134.02 826.39 500.51 3106.61 1288.30 10098.50 296.73
## [267] 464.59 760.17 750.34 2085.70 48.06 227.90 873.60
## [274] 606.11 923.51 691.64 233.20 1402.55 32.31 136.86
## [281] 1083.35 598.50 7055.78 25.88 498.56 3494.46 215.51
## [288] 5715.91 80.41 114.24 762.62 3200.76 5.50 505.63
## [295] 512.20 1413.95 740.74 5373.20 2326.88 101.93 57.70
## [302] 385.35 1277.17 607.00 564.31 276.28 496.73 480.73
## [309] 878.76 1617.76 62.22 349.80 532.92 367.71 2681.86
## [316] 1078.75 12586.90 2912.89 114.69 235.50 1135.49 2474.91
## [323] 489.54 94.05 382.99 820.04 201.32 1870.79 152.14
## [330] 1378.84 333.88 94.43 3691.55 626.00 583.52 763.66
## [337] 226.36 1823.50 7392.60 851.71 193.02 436.80 1409.48
## [344] 208.84 427.55 4864.11 474.25 1561.97 316.86 693.07
## [351] 1471.99 1690.67 205.66 73.59 522.83 168.12 2870.09
## [358] 4575.82 566.76 4412.63 999.02 22959.00 1941.65 399.58
## [365] 613.32 3795.32 511.93 2217.83 1069.28 169.61 1643.03
## [372] 50.58 1933.55 431.16 81.33 319.93 568.90 1537.07
## [379] 6042.72 561.90 1056.71 47106.50 889.15 233.11 388.16
## [386] 2032.07 512.78 3011.76 920.72 690.54 481.91 2047.56
## [393] 1647.79 220.36 3689.19 119.01 1072.89 390.31 1715.33
## [400] 7263.71 9216.46 1790.27 2267.03 1307.49 75.86 2061.29
## [407] 19798.90 960.36 54.66 414.66 2085.13 1092.76 1526.12
## [414] 554.65 1346.45 1443.58 581.21 3459.56 2836.08 2708.54
## [421] 3118.43 746.42 5301.05 942.41 3331.50 36123.40 2796.56
## [428] 170.12 667.40 567.63 554.54 2927.57 750.85 2215.35
## [435] 1981.13 2446.33 164.15 623.17 229.10 347.59 4579.47
## [442] 965.86 19.92 1119.13 6106.78 881.23 4200.84 32518.90
## [449] 4880.51 343.32 993.54 2840.81 711.50 1254.79 739.49
## [456] 732.21 3252.44 6308.05 321.43 1180.66 22.79 1984.33
## [463] 913.17 4962.24 4388.86 11068.60 2487.82 5087.50 1472.52
## [470] 822.40 18919.40 1684.01 377.60 224.81 1684.21 658.91
## [477] 1094.45 75.77 130.79 1412.76 125.63 2554.09 1702.58
## [484] 45.08 1858.42 774.25 7441.46 1167.94 49976.20 5063.82
## [491] 576.89 1265.29 3137.79 1107.68 5302.38 1441.09 720.36
## [498] 4573.48 483.10 2658.66 3429.01 1882.53 2522.31 243.81
## [505] 725.17 5471.99 596.72 31934.90 749.74 2391.69 4273.66
## [512] 196.03 9784.56 1557.66 1911.13 693.04 4613.15 2660.68
## [519] 849.79 3479.68 2255.94 304.79 10753.80 1787.56 558.05
## [526] 1805.45 1269.47 655.88 5306.54 244.20 2434.08 386.83
## [533] 986.55 586.73 499.85 620.87 732.43 2151.07 1267.83
## [540] 3304.77 477.89 132.10 766.88 366.20 1168.58 2274.47
## [547] 976.38 779.37 2474.64 183.40 440.95 1543.60 9070.65
## [554] 1296.75 1163.10 6292.61 3406.61 493.08 2318.11 5720.56
## [561] 1136.42 162.29 7905.27 20.21 899.28 129.52 1315.33
## [568] 4161.23 426.58 422.50 1259.00 1089.87 3780.69 4118.47
## [575] 34840.30 7190.11 900735.00 62750.40 238.75 1721.87 6060.91
## [582] 4593.29 20056.80 1137.66 3425.98 11587.20 14641.30 11493.80
## [589] 12163.60 8086.96 9231.82 9236.96 18476.70 3161.42 121149.00
## [596] 461.18 1589.03 18128.60 3709.53 6858.84 8669.64 1775.55
## [603] 286.56 8511.84 5037.65 3021.52 5355.92 436.23 2229.71
## [610] 1112.61 20241.90 14630.50 1370.28 12542.50 69256.80 14538.30
## [617] 883.83 1166.80 2904.37 1376.82 598.14 5422.26 5061.07
## [624] 7666.80 905.48 4242.92 260.88 1609.83 794.47 15251.00
## [631] 39657.70 72.49 1323.60 3939.83 5807.39 2846.66 884.99
## [638] 2423.74 375.30 587.83 0.46 450.03 274.65 3215.16
## [645] 76.17 917.55 5236.45 2976.51 559.30 410.44 3209.39
## [652] 2524.68 15868.40 5580.80 209.30 5688.59 76722.10 17179.00
## [659] 574.26 1991.54 2665.72 690.53 1689.51 1317.79 3426.73
## [666] 2200.13 578.66 4046.65 985.43 12330.70 5599.51 2276.97
## [673] 467.09 11546.50 699.55 182.71 216.96 785.52 656.77
## [680] 1949.02 325.56 691.26 1906.60 802.67 1189.79 1553.68
## [687] 1131.20 1099.51 2838.79 9732.82 1073.08 124.26 360.75
## [694] 611.56 128.47 1598.66 185.63 535.22 815.28 1619.79
## [701] 146.65 147.32 1461.98 947.58 6491.57 1518.45 4249.15
## [708] 1091.21 21204.90 2015.43 73.20 889.20 2575.65 312.96
## [715] 2726.24 1563.82 654.51 245.42 2484.21 192.93 1856.92
## [722] 281.98 478.91 843.46 4168.46 296.54 4144.78 1101.40
## [729] 525.02 4874.08 54333.10 536.87 768.82 382.45 4093.29
## [736] 631.99 1369.20 1399.54 266.52 2099.77 2810.98 5503.51
## [743] 218.21 814.80 488.63 669.18 9247.45 2572.76 273.24
## [750] 8464.39 1702.37 202871.00 2942.39 87.40 629.72 3574.60
## [757] 808.95 534.52 5383.92 647.27 3093.55 2682.75 2875.99
## [764] 1345.06 3718.44 604.29 1512.55 97.31 73919.00 7133.86
## [771] 6704.79 1502.74 5662.73 678.13 986.71 25608.40 218.03
## [778] 622.49 3245.92 946.77 1180.70 712.92 2053.41 220.80
## [785] 2019.74 943.81 599.59 1694.31 806.75 2644.97 6090.91
## [792] 4091.49 137.73 4811.33 489.09 28528.20 303.25 790.06
## [799] 1224.30 658.42 2231.39 1608.67 915.47 1996.20 1118.52
## [806] 822.59 1302.15 3720.79 803.32 6218.94 540.85 637.05
## [813] 43606.40 9865.87 142.08 510.26 3407.94 824.91 2521.46
## [820] 1136.81 4913.07 2707.57 1036.27 360.95 821.76 8076.13
## [827] 7832.08 1670.72 3150.22 235.04 14701.40 534.56 96.46
## [834] 279.66 1314.31 507.01 530.60 497.08 239.94 1131.24
## [841] 1741.49 85.16 290.73 1516.94 333.78
range(qt1_5$Weight) #0.46-900735.00
## [1] 0.46 900735.00
# To-do : normalise the weights to better visualise in graph. Convert to csv maybe.
Graph 2 Analysis:
qt2 <- data.table::fread(here::here("data", "Q1-Graph2.csv"))
head(qt2)
## Source eType Target Time Weight SourceLocation TargetLocation
## 1: 563211 4 564798 -732727926 0.0188679 NA NA
## 2: 563211 4 627390 -496596726 0.2000000 NA NA
## 3: 563211 4 561114 -277745526 0.2500000 NA NA
## 4: 541017 4 601492 -64423926 0.1428570 NA NA
## 5: 572413 1 629627 1296000 1.0000000 4 4
## 6: 572413 1 505965 1302571 1.0000000 4 4
## SourceLatitude SourceLongitude TargetLatitude TargetLongitude
## 1: NA NA NA NA
## 2: NA NA NA NA
## 3: NA NA NA NA
## 4: NA NA NA NA
## 5: -2.24962 -165.651 -1.16067 -162.983
## 6: -2.24962 -165.651 -3.88606 -166.186
tail(qt2)
## Source eType Target Time Weight SourceLocation TargetLocation
## 1: 527597 5 503701 31536000 761.27 NA NA
## 2: 527597 5 644226 31536000 981.94 NA NA
## 3: 527597 5 632961 31536000 207.22 NA NA
## 4: 527597 5 473173 31536000 820.07 NA NA
## 5: 527597 5 620120 31536000 1277.46 NA NA
## 6: 527597 5 621924 31536000 273.83 NA NA
## SourceLatitude SourceLongitude TargetLatitude TargetLongitude
## 1: NA NA NA NA
## 2: NA NA NA NA
## 3: NA NA NA NA
## 4: NA NA NA NA
## 5: NA NA NA NA
## 6: NA NA NA NA
# Summarising the Data:
summary(qt2)
## Source eType Target Time
## Min. :464459 Min. :0.000 Min. :459381 Min. :-732727926
## 1st Qu.:527597 1st Qu.:1.000 1st Qu.:515794 1st Qu.: 22734657
## Median :552988 Median :5.000 Median :575030 Median : 31536000
## Mean :560521 Mean :3.452 Mean :562981 Mean : 24176653
## 3rd Qu.:602912 3rd Qu.:5.000 3rd Qu.:620120 3rd Qu.: 31536000
## Max. :656156 Max. :6.000 Max. :657173 Max. : 31536000
##
## Weight SourceLocation TargetLocation SourceLatitude
## Min. : 0.02 Min. :0.00 Min. :1.00 Min. :-29.452
## 1st Qu.: 1.00 1st Qu.:2.00 1st Qu.:2.00 1st Qu.:-25.422
## Median : 216.69 Median :3.00 Median :3.00 Median : -3.886
## Mean : 1207.35 Mean :2.91 Mean :2.93 Mean :-12.048
## 3rd Qu.: 754.66 3rd Qu.:4.00 3rd Qu.:4.00 3rd Qu.: -1.161
## Max. :196567.00 Max. :4.00 Max. :4.00 Max. : 33.000
## NA's :1099 NA's :1099 NA's :1099
## SourceLongitude TargetLatitude TargetLongitude
## Min. :-166.19 Min. :-29.452 Min. :-168.472
## 1st Qu.:-162.98 1st Qu.:-25.422 1st Qu.:-162.983
## Median :-111.68 Median :-20.657 Median :-111.678
## Mean : -91.90 Mean :-12.702 Mean : -85.901
## 3rd Qu.: -13.37 3rd Qu.: -1.161 3rd Qu.: -9.462
## Max. : 91.00 Max. : 6.715 Max. : 91.784
## NA's :1099 NA's :1099 NA's :1099
nrow(qt2) #1300
## [1] 1300
ncol(qt2) #11
## [1] 11
qt2$Source <- as.character(qt2$Source)
qt2$Target <- as.character(qt2$Target)
# Differentiating between channels:
qt2_01 <- qt2 %>% filter(qt2$eType == 0 | qt2$eType == 1) # Communication Channel
nrow(qt2_01) # 435
## [1] 435
qt2_23 <- qt2 %>% filter(qt2$eType == 2 | qt2$eType == 3) # Procurement Channel
nrow(qt2_23) # 14
## [1] 14
qt2_4 <- qt2 %>% filter(qt2$eType == 4) # Co-authorship Channel
nrow(qt2_4) # 4
## [1] 4
qt2_5 <- qt2 %>% filter(qt2$eType == 5) # Demographic Channel
nrow(qt2_5) # 823
## [1] 823
qt2_6 <- qt2 %>% filter(qt2$eType == 6) # Travel Channel
nrow(qt2_6) # 24
## [1] 24
# Highest data for Demographic, Communication and Travel Channel.
# Analysis of the Communication channel:
glimpse(qt2_01)
## Observations: 435
## Variables: 11
## $ Source <chr> "572413", "572413", "505965", "572413", "62962...
## $ eType <int> 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1...
## $ Target <chr> "629627", "505965", "629627", "505965", "51579...
## $ Time <int> 1296000, 1302571, 1308663, 1316274, 1316615, 1...
## $ Weight <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1...
## $ SourceLocation <int> 4, 4, NA, 4, 4, NA, 4, 4, 4, 4, 4, NA, 4, NA, ...
## $ TargetLocation <int> 4, 4, NA, 4, 4, NA, 4, 4, 4, 4, 4, NA, 4, NA, ...
## $ SourceLatitude <dbl> -2.24962, -2.24962, NA, -2.24962, -1.16067, NA...
## $ SourceLongitude <dbl> -165.651, -165.651, NA, -165.651, -162.983, NA...
## $ TargetLatitude <dbl> -1.16067, -3.88606, NA, -3.88606, 6.71518, NA,...
## $ TargetLongitude <dbl> -162.983, -166.186, NA, -166.186, -165.251, NA...
#unique(qt2_01)
unique(qt2_01$eType) # 0 1
## [1] 1 0
unique(qt2_01$SourceLocation)
## [1] 4 NA 1 3 2
unique(qt2_01$TargetLocation)
## [1] 4 NA 1 2 3
unique(qt2_01$SourceLatitude)
## [1] -2.24962 NA -1.16067 6.71518 5.62833 -29.45240 -26.66880
## [8] -27.55500 -3.88606 -28.38010 -24.71710 -25.42200 -24.01270
unique(qt2_01$SourceLongitude)
## [1] -165.65100 NA -162.98300 -165.25100 -161.11300 -13.64910
## [7] -7.31949 -13.37300 -166.18600 -9.46184 -111.47400 -111.67800
## [13] 90.97340
unique(qt2_01$TargetLatitude)
## [1] -1.160670 -3.886060 NA 6.715180 -27.335300 -29.452400
## [7] 2.747850 -27.555000 5.628330 0.486228 -26.668800 -24.012700
## [13] -24.717100 -25.422000 -20.656500 -28.380100
unique(qt2_01$TargetLongitude)
## [1] -162.98300 -166.18600 NA -165.25100 -18.22270 -13.64910
## [7] -162.27500 -13.37300 -161.11300 -168.47200 -7.31949 90.97340
## [13] -111.47400 -111.67800 91.78410 -9.46184
unique(qt2_01$Source)
## [1] "572413" "505965" "629627" "515794" "541017" "585212" "599441"
## [8] "582851" "527597" "563211" "534034" "644830" "488928" "602912"
## [15] "477138" "544615" "534449" "639051"
unique(qt2_01$Target)
## [1] "629627" "505965" "515794" "563211" "541017" "599441" "527597"
## [8] "585212" "534034" "582851" "488928" "644830" "534449" "477138"
## [15] "639051" "544615" "602912"
colnames(qt2_01)
## [1] "Source" "eType" "Target"
## [4] "Time" "Weight" "SourceLocation"
## [7] "TargetLocation" "SourceLatitude" "SourceLongitude"
## [10] "TargetLatitude" "TargetLongitude"
# Analysis of the Demographic channel:
glimpse(qt2_5)
## Observations: 823
## Variables: 11
## $ Source <chr> "604021", "604021", "510031", "604021", "55298...
## $ eType <int> 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5...
## $ Target <chr> "630626", "536346", "604021", "520660", "60402...
## $ Time <int> 31536000, 31536000, 31536000, 31536000, 315360...
## $ Weight <dbl> 2258.44, 561.50, 113.92, 881.17, 7756.23, 134....
## $ SourceLocation <int> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLocation <int> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ SourceLatitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ SourceLongitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLatitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLongitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
#unique(qt2_5)
unique(qt2_5$eType) # 5
## [1] 5
unique(qt2_5$SourceLocation) # NA
## [1] NA
unique(qt2_5$TargetLocation) # NA
## [1] NA
unique(qt2_5$SourceLatitude) # NA
## [1] NA
unique(qt2_5$SourceLongitude) # NA
## [1] NA
unique(qt2_5$TargetLatitude) # NA
## [1] NA
unique(qt2_5$TargetLongitude) # NA
## [1] NA
unique(qt2_5$Source)
## [1] "604021" "510031" "552988" "533094" "606043" "595057" "634181"
## [8] "548320" "505965" "572413" "515794" "563584" "629627" "534034"
## [15] "599441" "585212" "536953" "620120" "515799" "656156" "552439"
## [22] "546478" "488928" "602912" "533024" "499312" "464563" "546626"
## [29] "544615" "533141" "471663" "501047" "534449" "472522" "477138"
## [36] "475811" "590265" "653390" "573870" "645210" "639051" "582851"
## [43] "541017" "563211" "527597"
unique(qt2_5$Target)
## [1] "630626" "536346" "604021" "520660" "527449" "459381" "595298"
## [8] "466907" "577992" "580426" "595581" "616315" "503701" "571970"
## [15] "644226" "632961" "473173" "620120" "575030" "621924" "640784"
## [22] "533094" "567195" "537281" "523927" "642329" "606043" "589943"
## [29] "503218" "595057" "634181" "548320" "606730" "505965" "572413"
## [36] "515794" "563584" "629627" "534034" "599441" "585212" "536953"
## [43] "515799" "656156" "552439" "546478" "488928" "602912" "533024"
## [50] "499312" "464563" "546626" "544615" "533141" "471663" "501047"
## [57] "534449" "472522" "477138" "475811" "590265" "653390" "573870"
## [64] "645210" "639051" "582851" "541017" "563211" "527597"
unique(qt2_5$Weight)
## [1] 2258.44 561.50 113.92 881.17 7756.23 134.84 193.22
## [8] 355.82 209.22 31.35 132.22 421.43 234.74 176.53
## [15] 84.22 766.83 92.79 1234.60 473.95 1236.75 658.78
## [22] 318.41 3402.76 285.79 26.94 2267.78 25708.90 1613.63
## [29] 370.94 284.32 782.50 242.12 1395.87 497.09 1242.83
## [36] 1332.94 148.27 2402.81 78.91 924.08 110.68 1348.11
## [43] 5654.70 2361.75 499.47 22.11 1829.16 17608.30 373.74
## [50] 52.30 288.20 520.41 412.72 1457.54 804.23 993.32
## [57] 639.26 260.21 76.04 210.77 112.26 1067.92 2296.04
## [64] 6003.36 206.77 1361.75 167.12 5705.36 97.02 99.71
## [71] 337.97 419.67 272.56 561.93 28.62 273.79 913.80
## [78] 129.16 855.02 863.35 4289.16 350.13 2609.07 800.36
## [85] 2233.87 15174.50 184.39 267.63 299.54 469.30 729.69
## [92] 1370.33 912.34 65.04 32.69 354.00 1164.48 47.31
## [99] 811.15 402.65 228.04 3565.20 2201.95 479.23 1270.54
## [106] 477.22 601.85 333.79 13557.00 878.46 64.15 340.62
## [113] 1531.39 500.35 448.03 357.11 791.93 13.93 520.35
## [120] 292.58 488.52 139.89 156.49 115.48 1123.42 1071.33
## [127] 3982.11 575.08 3348.11 271.34 1221.26 9945.54 3171.42
## [134] 79.82 227.65 82.96 322.05 489.12 572.58 515.71
## [141] 141.30 78.42 874.89 61.62 881.15 126.48 1141.88
## [148] 1428.67 647.87 88.82 1983.14 428.32 390.65 12652.90
## [155] 1743.69 73.26 295.58 754.28 187.96 187.52 447.60
## [162] 426.93 7.71 228.08 416.46 135.67 252.47 98.62
## [169] 2155.42 92.26 1596.67 584.60 153.68 460.23 1258.39
## [176] 135.71 81.80 223.74 891.28 458.25 117.13 658.22
## [183] 216.58 270.56 262.17 8.05 180.64 160.57 29.94
## [190] 377.60 146.35 347.88 2108.03 699.98 1691.94 11708.60
## [197] 233.94 551.66 483.37 88.39 693.99 668.48 489.58
## [204] 360.49 637.90 544.88 429.92 10.67 228.24 795.47
## [211] 939.88 319.50 336.04 6596.71 698.93 208.98 331.29
## [218] 701.57 554.90 40.21 485.15 79.87 54.06 372.04
## [225] 1001.63 41.97 854.79 822.54 1576.90 324.44 6909.84
## [232] 98.42 98.45 217.43 923.82 331.89 813.98 7.09
## [239] 24.66 243.16 196.86 519.34 37.46 159.21 359.29
## [246] 383.24 543.76 820.43 61.38 20.01 173.66 876.96
## [253] 0.17 149.80 41.42 440.57 63.91 68.27 277.77
## [260] 305.08 19.66 38.91 166.02 465.15 107.62 7023.93
## [267] 313.91 91.47 213.36 1168.03 237.14 449.99 556.72
## [274] 23.93 470.65 512.49 203.52 217.05 53.70 196.97
## [281] 116.19 233.26 6721.34 457.96 100.10 972.12 1530.76
## [288] 140.95 1330.24 1151.36 129.36 730.47 49.27 404.72
## [295] 684.01 1382.90 423.04 1534.03 617.00 1970.27 5150.48
## [302] 820.48 129.81 544.86 446.02 349.45 1011.71 683.75
## [309] 32.88 683.83 2272.00 144.34 475.94 688.32 3746.87
## [316] 13710.20 1205.77 20.87 543.68 719.01 335.87 1291.50
## [323] 398.58 362.16 412.75 70.98 557.16 879.41 369.95
## [330] 768.46 17.64 435.05 315.55 1089.36 4849.31 654.53
## [337] 244.14 13256.90 862.40 241.27 264.21 1949.10 407.88
## [344] 1173.18 485.44 212.58 365.46 738.10 603.48 433.68
## [351] 1827.65 384.62 229.16 742.59 35.23 4391.67 652.46
## [358] 8367.13 1323.35 47.57 71.09 634.80 318.20 1477.07
## [365] 456.72 494.24 37.01 1607.20 13.42 234.60 960.31
## [372] 1156.32 9595.78 600.97 618.86 7091.58 1106.18 2655.89
## [379] 20518.60 4060.69 77.62 355.15 1888.31 320.76 773.91
## [386] 6.50 25.88 1681.76 532.08 208.72 1713.46 1199.93
## [393] 456.15 226.36 164.14 1944.15 748.17 1941.85 744.35
## [400] 2191.45 18351.20 943.00 63.04 401.38 1754.04 279.50
## [407] 4242.50 519.27 428.19 729.65 352.81 1079.16 9.53
## [414] 543.70 272.54 1776.52 282.64 4800.15 2270.29 34513.10
## [421] 3896.34 122.51 748.85 1087.88 636.80 1271.14 838.17
## [428] 3030.47 629.02 894.90 1483.20 2764.54 622.46 1598.44
## [435] 2385.08 221.07 1421.09 3749.53 1044.11 691.62 1127.74
## [442] 19434.50 303.66 611.34 1652.08 596.25 498.96 210.09
## [449] 848.71 722.75 644.66 1661.06 103.71 1801.64 123.72
## [456] 206.09 2609.85 1313.85 17.46 6057.31 107.87 2362.89
## [463] 40893.30 3770.63 241.36 499.73 1287.29 275.05 832.72
## [470] 824.99 2432.58 419.41 2302.42 1479.93 498.09 2106.71
## [477] 5.50 663.04 328.49 171.99 5338.67 5816.30 1513.56
## [484] 13128.40 1910.13 422.90 653.41 619.61 224.34 843.58
## [491] 459.16 296.40 431.55 507.64 538.93 316.14 1389.58
## [498] 1430.00 1403.88 14125.60 1209.50 185.85 138.81 4226.85
## [505] 292.64 497.49 441.68 1859.23 171.51 909.43 944.79
## [512] 29.26 2483.79 133.20 458.40 964.83 687.54 16.56
## [519] 213.04 12388.00 212.89 179.11 886.18 558.24 1199.16
## [526] 203.90 85.73 1197.33 757.71 292.42 2727.48 105.77
## [533] 362.27 2263.32 1499.45 2176.30 791.50 14177.30 68.49
## [540] 125.72 2279.98 235.75 1158.45 382.24 372.92 589.65
## [547] 403.43 2341.83 401.77 1616.43 1252.03 67.22 194.61
## [554] 629.48 10817.20 929.07 137.84 591.71 2671.77 485.28
## [561] 251.56 2970.58 282.30 826.02 737.78 269.63 2476.78
## [568] 26.77 1144.80 1016.19 4418.43 1185.68 2249.89 216.81
## [575] 813.87 3004.24 322.32 665.70 10.19 605.53 7.18
## [582] 2109.64 198.29 285.36 395.95 2352.91 5748.55 518.51
## [589] 149.26 72.22 751.42 622.66 627.20 132.09 436.19
## [596] 233.23 2178.34 1014.78 3103.23 222.45 152.82 1699.98
## [603] 693.40 1990.33 5714.39 245.84 323.70 298.45 348.78
## [610] 185.98 1048.98 194.30 420.67 309.72 957.56 777.37
## [617] 39.66 330.35 258.62 277.92 4111.40 119.59 434.28
## [624] 316.24 5.48 228.28 265.86 1201.20 102.41 723.10
## [631] 39.47 116.78 121.89 966.10 2365.02 8856.87 384.70
## [638] 279.16 856.28 643.53 494.53 276.79 438.82 489.27
## [645] 1117.11 155.39 487.37 357.90 411.14 141.13 1069.34
## [652] 752.56 12740.80 1592.10 724.17 10042.30 127.56 358.62
## [659] 431.14 1064.83 99.86 509.25 890.84 336.03 548.16
## [666] 948.67 415.63 331.71 113.71 251.39 1492.32 164.80
## [673] 1763.26 31.08 2228.22 356.61 3019.34 241.38 620.70
## [680] 414.28 257.91 1416.17 20.72 639.76 99.74 481.03
## [687] 435.73 184.64 746.46 274.71 415.50 351.06 1170.20
## [694] 4792.16 437.54 29973.60 278.77 713.63 1592.06 550.46
## [701] 157.68 418.13 1223.88 37.94 311.95 2090.93 408.57
## [708] 1135.98 1024.90 427.59 1480.23 6687.72 9218.86 8012.80
## [715] 196567.00 13536.00 131.53 504.52 363.71 628.37 3250.02
## [722] 3604.06 74.73 1281.50 4821.65 3029.73 1839.38 2175.30
## [729] 47680.00 11164.10 339.98 5865.03 1010.50 1548.47 18671.50
## [736] 2519.64 59.25 592.99 918.16 274.50 1765.12 26.02
## [743] 687.27 674.77 1318.01 650.69 1331.52 127.16 629.85
## [750] 945.16 4056.11 3336.95 823.05 3583.08 21.36 289.46
## [757] 2432.00 28827.50 6094.45 276.94 635.57 3947.64 820.82
## [764] 729.14 3067.24 195.49 1935.69 3866.28 3532.11 484.08
## [771] 180.92 1529.05 431.03 642.78 3517.98 8084.37 1292.87
## [778] 4267.76 464.86 2700.90 33865.00 5301.34 96.34 325.71
## [785] 2348.19 801.11 1121.43 2947.72 855.53 2739.30 908.48
## [792] 820.14 1218.25 2401.99 286.60 212.56 2758.33 6505.41
## [799] 855.88 440.68 3860.15 401.15 1609.38 18210.20 2346.63
## [806] 202.12 680.91 548.87 755.80 273.80 385.10 406.02
## [813] 167.01 352.52 412.29 761.27 981.94 207.22 820.07
## [820] 1277.46 273.83
qt2_5 <- subset(qt2_5, select = -c(SourceLocation, TargetLocation, SourceLatitude, SourceLongitude, TargetLatitude, TargetLongitude)) # SOurce and Target Latitude and Longitude columns removed as all Null.
colnames(qt2_5)
## [1] "Source" "eType" "Target" "Time" "Weight"
any(qt2_5$Source) == any(qt2_5$Target) # True
## Warning in any(qt2_5$Source): coercing argument of type 'character' to
## logical
## Warning in any(qt2_5$Target): coercing argument of type 'character' to
## logical
## [1] NA
range(qt2_5$Source) # 464563-656156
## [1] "464563" "656156"
range(qt2_5$Target) # 459381-656156
## [1] "459381" "656156"
range(qt2_5$Time) # 31536000-31536000
## [1] 31536000 31536000
income_cat_qt2 <- NULL
# Income Categories:
for (i in (qt2_5$Source)) {
for (j in (cat$NodeID)) { # cat_list contains all the demographic nodeIDs (from the DemographicNodeExtraction Script)
if(i == j){
income_cat_qt2 <- append(income_cat_qt2,i)
}
}
}
print(income_cat_qt2) # income categories extracted
## [1] "510031" "552988" "510031" "552988" "510031" "552988" "510031"
## [8] "552988" "552988" "510031" "552988" "552988" "552988" "510031"
## [15] "552988" "552988" "510031" "552988" "552988" "552988" "552988"
## [22] "552988" "620120" "552988" "552988" "510031" "552988" "510031"
## [29] "552988" "620120" "552988" "620120" "552988" "510031" "552988"
## [36] "510031" "552988" "552988" "552988" "552988" "510031" "552988"
## [43] "620120" "510031" "552988" "552988" "620120" "552988" "552988"
## [50] "620120" "552988" "620120" "510031" "552988" "620120" "552988"
## [57] "620120" "510031" "552988" "510031" "552988" "510031" "552988"
## [64] "510031" "552988" "552988" "510031" "552988" "510031" "552988"
## [71] "552988"
unique(income_cat_qt2) # 3
## [1] "510031" "552988" "620120"
qt2_5_sub1 <- subset(qt2_5, qt2_5$Source == income_cat_qt2) # Subset of data with only income categories
## Warning in qt2_5$Source == income_cat_qt2: longer object length is not a
## multiple of shorter object length
str(qt2_5_sub1)
## 'data.frame': 38 obs. of 5 variables:
## $ Source: chr "510031" "552988" "552988" "510031" ...
## $ eType : int 5 5 5 5 5 5 5 5 5 5 ...
## $ Target: chr "604021" "533094" "606043" "595057" ...
## $ Time : int 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 ...
## $ Weight: num 114 25709 17608 167 5705 ...
plot(qt2_5_sub1$Source, qt2_5_sub1$Weight) # Plot of Monetary income in each category
# Expense Categories:
expense_cat_qt2 <- NULL
for (k in qt2_5$Target) {
for(l in cat$NodeID){
if(k==l){
expense_cat_qt2 <- append(expense_cat_qt2, k)
}
}
}
print(expense_cat_qt2) # expense categories extracted
## [1] "630626" "536346" "520660" "527449" "459381" "595298" "466907"
## [8] "577992" "580426" "595581" "616315" "503701" "571970" "644226"
## [15] "632961" "473173" "620120" "575030" "621924" "640784" "630626"
## [22] "536346" "520660" "567195" "527449" "459381" "595298" "466907"
## [29] "577992" "537281" "523927" "616315" "642329" "503701" "571970"
## [36] "644226" "632961" "473173" "620120" "630626" "536346" "520660"
## [43] "567195" "527449" "459381" "595298" "466907" "589943" "577992"
## [50] "523927" "595581" "616315" "571970" "644226" "632961" "473173"
## [57] "620120" "575030" "503218" "630626" "567195" "527449" "459381"
## [64] "595298" "466907" "589943" "580426" "642329" "503701" "632961"
## [71] "473173" "620120" "575030" "621924" "630626" "536346" "520660"
## [78] "527449" "459381" "595298" "466907" "589943" "577992" "523927"
## [85] "580426" "595581" "642329" "503701" "571970" "644226" "632961"
## [92] "473173" "620120" "575030" "503218" "630626" "536346" "520660"
## [99] "567195" "527449" "459381" "595298" "466907" "606730" "537281"
## [106] "523927" "595581" "616315" "642329" "503701" "571970" "644226"
## [113] "632961" "473173" "620120" "575030" "621924" "630626" "536346"
## [120] "520660" "567195" "527449" "459381" "595298" "466907" "577992"
## [127] "537281" "523927" "580426" "595581" "503701" "571970" "644226"
## [134] "473173" "620120" "575030" "621924" "640784" "630626" "536346"
## [141] "520660" "567195" "527449" "459381" "595298" "466907" "580426"
## [148] "595581" "616315" "642329" "503701" "644226" "632961" "473173"
## [155] "620120" "575030" "621924" "630626" "536346" "520660" "567195"
## [162] "527449" "459381" "595298" "589943" "577992" "523927" "580426"
## [169] "595581" "642329" "571970" "644226" "632961" "473173" "620120"
## [176] "621924" "503218" "630626" "536346" "520660" "527449" "459381"
## [183] "595298" "466907" "589943" "577992" "537281" "523927" "616315"
## [190] "642329" "503701" "571970" "644226" "473173" "620120" "575030"
## [197] "567195" "527449" "459381" "595298" "589943" "537281" "523927"
## [204] "580426" "595581" "642329" "503701" "571970" "473173" "620120"
## [211] "575030" "503218" "567195" "527449" "459381" "595298" "466907"
## [218] "589943" "523927" "580426" "595581" "642329" "503701" "571970"
## [225] "632961" "473173" "620120" "621924" "567195" "527449" "459381"
## [232] "595298" "466907" "589943" "537281" "523927" "580426" "595581"
## [239] "616315" "503701" "571970" "632961" "473173" "620120" "621924"
## [246] "567195" "527449" "459381" "595298" "466907" "589943" "577992"
## [253] "580426" "595581" "616315" "642329" "503701" "632961" "473173"
## [260] "620120" "621924" "567195" "527449" "459381" "595298" "466907"
## [267] "589943" "577992" "537281" "523927" "580426" "595581" "616315"
## [274] "503701" "632961" "473173" "575030" "567195" "527449" "459381"
## [281] "595298" "466907" "589943" "523927" "580426" "616315" "503701"
## [288] "632961" "473173" "620120" "621924" "567195" "527449" "459381"
## [295] "595298" "466907" "589943" "577992" "537281" "523927" "580426"
## [302] "595581" "616315" "642329" "503701" "571970" "632961" "473173"
## [309] "620120" "575030" "630626" "567195" "527449" "459381" "595298"
## [316] "466907" "589943" "577992" "537281" "523927" "595581" "616315"
## [323] "642329" "503701" "632961" "473173" "620120" "621924" "630626"
## [330] "567195" "527449" "459381" "595298" "466907" "589943" "523927"
## [337] "616315" "642329" "503701" "571970" "632961" "473173" "575030"
## [344] "621924" "503218" "630626" "536346" "520660" "567195" "527449"
## [351] "459381" "595298" "466907" "606730" "577992" "537281" "523927"
## [358] "580426" "616315" "503701" "644226" "632961" "473173" "575030"
## [365] "621924" "630626" "536346" "520660" "567195" "527449" "459381"
## [372] "595298" "466907" "589943" "537281" "523927" "616315" "642329"
## [379] "503701" "571970" "644226" "473173" "620120" "640784" "630626"
## [386] "567195" "527449" "459381" "595298" "466907" "577992" "537281"
## [393] "523927" "580426" "595581" "642329" "503701" "632961" "473173"
## [400] "620120" "575030" "621924" "630626" "536346" "520660" "527449"
## [407] "459381" "595298" "466907" "577992" "537281" "523927" "616315"
## [414] "642329" "503701" "571970" "644226" "632961" "473173" "620120"
## [421] "575030" "621924" "630626" "536346" "520660" "567195" "527449"
## [428] "459381" "595298" "466907" "606730" "589943" "577992" "537281"
## [435] "523927" "595581" "642329" "503701" "571970" "644226" "632961"
## [442] "473173" "620120" "575030" "621924" "567195" "527449" "459381"
## [449] "595298" "466907" "589943" "577992" "580426" "595581" "642329"
## [456] "503701" "632961" "473173" "620120" "621924" "567195" "527449"
## [463] "459381" "595298" "466907" "589943" "537281" "523927" "580426"
## [470] "595581" "616315" "642329" "503701" "571970" "632961" "473173"
## [477] "620120" "621924" "527449" "459381" "595298" "466907" "589943"
## [484] "537281" "580426" "595581" "616315" "642329" "503701" "571970"
## [491] "632961" "473173" "621924" "567195" "527449" "459381" "595298"
## [498] "466907" "589943" "577992" "595581" "616315" "642329" "503701"
## [505] "632961" "473173" "620120" "575030" "621924" "503218" "567195"
## [512] "527449" "459381" "595298" "466907" "589943" "523927" "580426"
## [519] "595581" "616315" "642329" "503701" "632961" "473173" "575030"
## [526] "630626" "527449" "459381" "595298" "466907" "589943" "537281"
## [533] "595581" "616315" "503701" "473173" "620120" "575030" "630626"
## [540] "567195" "527449" "459381" "595298" "466907" "606730" "589943"
## [547] "580426" "595581" "616315" "642329" "503701" "571970" "473173"
## [554] "575030" "621924" "567195" "527449" "459381" "595298" "466907"
## [561] "577992" "537281" "523927" "580426" "595581" "616315" "571970"
## [568] "473173" "527449" "459381" "595298" "466907" "589943" "537281"
## [575] "523927" "595581" "616315" "642329" "632961" "473173" "575030"
## [582] "567195" "527449" "459381" "595298" "466907" "589943" "577992"
## [589] "537281" "523927" "580426" "616315" "642329" "503701" "632961"
## [596] "473173" "575030" "621924" "567195" "527449" "459381" "595298"
## [603] "466907" "606730" "589943" "577992" "537281" "523927" "580426"
## [610] "595581" "616315" "642329" "503701" "571970" "473173" "620120"
## [617] "621924" "527449" "459381" "595298" "466907" "577992" "537281"
## [624] "523927" "580426" "595581" "616315" "642329" "503701" "632961"
## [631] "473173" "620120" "575030" "630626" "527449" "459381" "595298"
## [638] "466907" "589943" "577992" "537281" "523927" "580426" "595581"
## [645] "616315" "642329" "503701" "632961" "473173" "620120" "575030"
## [652] "630626" "567195" "527449" "459381" "595298" "466907" "589943"
## [659] "577992" "537281" "580426" "595581" "642329" "503701" "473173"
## [666] "620120" "575030" "640784" "630626" "536346" "520660" "567195"
## [673] "527449" "459381" "595298" "466907" "589943" "577992" "537281"
## [680] "580426" "595581" "642329" "503701" "644226" "632961" "473173"
## [687] "620120" "575030" "503218" "630626" "536346" "520660" "567195"
## [694] "527449" "459381" "595298" "466907" "606730" "589943" "577992"
## [701] "523927" "595581" "616315" "642329" "571970" "644226" "632961"
## [708] "473173" "620120" "575030" "621924" "630626" "536346" "567195"
## [715] "527449" "459381" "595298" "466907" "589943" "577992" "537281"
## [722] "523927" "580426" "595581" "642329" "503701" "644226" "632961"
## [729] "473173" "620120" "575030" "640784" "630626" "536346" "520660"
## [736] "567195" "527449" "459381" "595298" "466907" "577992" "537281"
## [743] "523927" "580426" "595581" "642329" "503701" "644226" "632961"
## [750] "473173" "620120" "621924"
unique(expense_cat_qt2) # 27
## [1] "630626" "536346" "520660" "527449" "459381" "595298" "466907"
## [8] "577992" "580426" "595581" "616315" "503701" "571970" "644226"
## [15] "632961" "473173" "620120" "575030" "621924" "640784" "567195"
## [22] "537281" "523927" "642329" "589943" "503218" "606730"
qt2_5_sub2 <- subset(qt2_5, qt2_5$Target == expense_cat_qt2) # Subset of data with only expense categories
## Warning in qt2_5$Target == expense_cat_qt2: longer object length is not a
## multiple of shorter object length
str(qt2_5_sub2)
## 'data.frame': 10 obs. of 5 variables:
## $ Source: chr "604021" "604021" "563584" "563584" ...
## $ eType : int 5 5 5 5 5 5 5 5 5 5
## $ Target: chr "630626" "536346" "589943" "642329" ...
## $ Time : int 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000
## $ Weight: num 2258 562 694 545 430 ...
plot(qt2_5_sub2$Target, qt2_5_sub2$Weight) # Plot of Monetary expenses in each category
hist(qt2_5$Weight)
unique(qt2_5$Weight)
## [1] 2258.44 561.50 113.92 881.17 7756.23 134.84 193.22
## [8] 355.82 209.22 31.35 132.22 421.43 234.74 176.53
## [15] 84.22 766.83 92.79 1234.60 473.95 1236.75 658.78
## [22] 318.41 3402.76 285.79 26.94 2267.78 25708.90 1613.63
## [29] 370.94 284.32 782.50 242.12 1395.87 497.09 1242.83
## [36] 1332.94 148.27 2402.81 78.91 924.08 110.68 1348.11
## [43] 5654.70 2361.75 499.47 22.11 1829.16 17608.30 373.74
## [50] 52.30 288.20 520.41 412.72 1457.54 804.23 993.32
## [57] 639.26 260.21 76.04 210.77 112.26 1067.92 2296.04
## [64] 6003.36 206.77 1361.75 167.12 5705.36 97.02 99.71
## [71] 337.97 419.67 272.56 561.93 28.62 273.79 913.80
## [78] 129.16 855.02 863.35 4289.16 350.13 2609.07 800.36
## [85] 2233.87 15174.50 184.39 267.63 299.54 469.30 729.69
## [92] 1370.33 912.34 65.04 32.69 354.00 1164.48 47.31
## [99] 811.15 402.65 228.04 3565.20 2201.95 479.23 1270.54
## [106] 477.22 601.85 333.79 13557.00 878.46 64.15 340.62
## [113] 1531.39 500.35 448.03 357.11 791.93 13.93 520.35
## [120] 292.58 488.52 139.89 156.49 115.48 1123.42 1071.33
## [127] 3982.11 575.08 3348.11 271.34 1221.26 9945.54 3171.42
## [134] 79.82 227.65 82.96 322.05 489.12 572.58 515.71
## [141] 141.30 78.42 874.89 61.62 881.15 126.48 1141.88
## [148] 1428.67 647.87 88.82 1983.14 428.32 390.65 12652.90
## [155] 1743.69 73.26 295.58 754.28 187.96 187.52 447.60
## [162] 426.93 7.71 228.08 416.46 135.67 252.47 98.62
## [169] 2155.42 92.26 1596.67 584.60 153.68 460.23 1258.39
## [176] 135.71 81.80 223.74 891.28 458.25 117.13 658.22
## [183] 216.58 270.56 262.17 8.05 180.64 160.57 29.94
## [190] 377.60 146.35 347.88 2108.03 699.98 1691.94 11708.60
## [197] 233.94 551.66 483.37 88.39 693.99 668.48 489.58
## [204] 360.49 637.90 544.88 429.92 10.67 228.24 795.47
## [211] 939.88 319.50 336.04 6596.71 698.93 208.98 331.29
## [218] 701.57 554.90 40.21 485.15 79.87 54.06 372.04
## [225] 1001.63 41.97 854.79 822.54 1576.90 324.44 6909.84
## [232] 98.42 98.45 217.43 923.82 331.89 813.98 7.09
## [239] 24.66 243.16 196.86 519.34 37.46 159.21 359.29
## [246] 383.24 543.76 820.43 61.38 20.01 173.66 876.96
## [253] 0.17 149.80 41.42 440.57 63.91 68.27 277.77
## [260] 305.08 19.66 38.91 166.02 465.15 107.62 7023.93
## [267] 313.91 91.47 213.36 1168.03 237.14 449.99 556.72
## [274] 23.93 470.65 512.49 203.52 217.05 53.70 196.97
## [281] 116.19 233.26 6721.34 457.96 100.10 972.12 1530.76
## [288] 140.95 1330.24 1151.36 129.36 730.47 49.27 404.72
## [295] 684.01 1382.90 423.04 1534.03 617.00 1970.27 5150.48
## [302] 820.48 129.81 544.86 446.02 349.45 1011.71 683.75
## [309] 32.88 683.83 2272.00 144.34 475.94 688.32 3746.87
## [316] 13710.20 1205.77 20.87 543.68 719.01 335.87 1291.50
## [323] 398.58 362.16 412.75 70.98 557.16 879.41 369.95
## [330] 768.46 17.64 435.05 315.55 1089.36 4849.31 654.53
## [337] 244.14 13256.90 862.40 241.27 264.21 1949.10 407.88
## [344] 1173.18 485.44 212.58 365.46 738.10 603.48 433.68
## [351] 1827.65 384.62 229.16 742.59 35.23 4391.67 652.46
## [358] 8367.13 1323.35 47.57 71.09 634.80 318.20 1477.07
## [365] 456.72 494.24 37.01 1607.20 13.42 234.60 960.31
## [372] 1156.32 9595.78 600.97 618.86 7091.58 1106.18 2655.89
## [379] 20518.60 4060.69 77.62 355.15 1888.31 320.76 773.91
## [386] 6.50 25.88 1681.76 532.08 208.72 1713.46 1199.93
## [393] 456.15 226.36 164.14 1944.15 748.17 1941.85 744.35
## [400] 2191.45 18351.20 943.00 63.04 401.38 1754.04 279.50
## [407] 4242.50 519.27 428.19 729.65 352.81 1079.16 9.53
## [414] 543.70 272.54 1776.52 282.64 4800.15 2270.29 34513.10
## [421] 3896.34 122.51 748.85 1087.88 636.80 1271.14 838.17
## [428] 3030.47 629.02 894.90 1483.20 2764.54 622.46 1598.44
## [435] 2385.08 221.07 1421.09 3749.53 1044.11 691.62 1127.74
## [442] 19434.50 303.66 611.34 1652.08 596.25 498.96 210.09
## [449] 848.71 722.75 644.66 1661.06 103.71 1801.64 123.72
## [456] 206.09 2609.85 1313.85 17.46 6057.31 107.87 2362.89
## [463] 40893.30 3770.63 241.36 499.73 1287.29 275.05 832.72
## [470] 824.99 2432.58 419.41 2302.42 1479.93 498.09 2106.71
## [477] 5.50 663.04 328.49 171.99 5338.67 5816.30 1513.56
## [484] 13128.40 1910.13 422.90 653.41 619.61 224.34 843.58
## [491] 459.16 296.40 431.55 507.64 538.93 316.14 1389.58
## [498] 1430.00 1403.88 14125.60 1209.50 185.85 138.81 4226.85
## [505] 292.64 497.49 441.68 1859.23 171.51 909.43 944.79
## [512] 29.26 2483.79 133.20 458.40 964.83 687.54 16.56
## [519] 213.04 12388.00 212.89 179.11 886.18 558.24 1199.16
## [526] 203.90 85.73 1197.33 757.71 292.42 2727.48 105.77
## [533] 362.27 2263.32 1499.45 2176.30 791.50 14177.30 68.49
## [540] 125.72 2279.98 235.75 1158.45 382.24 372.92 589.65
## [547] 403.43 2341.83 401.77 1616.43 1252.03 67.22 194.61
## [554] 629.48 10817.20 929.07 137.84 591.71 2671.77 485.28
## [561] 251.56 2970.58 282.30 826.02 737.78 269.63 2476.78
## [568] 26.77 1144.80 1016.19 4418.43 1185.68 2249.89 216.81
## [575] 813.87 3004.24 322.32 665.70 10.19 605.53 7.18
## [582] 2109.64 198.29 285.36 395.95 2352.91 5748.55 518.51
## [589] 149.26 72.22 751.42 622.66 627.20 132.09 436.19
## [596] 233.23 2178.34 1014.78 3103.23 222.45 152.82 1699.98
## [603] 693.40 1990.33 5714.39 245.84 323.70 298.45 348.78
## [610] 185.98 1048.98 194.30 420.67 309.72 957.56 777.37
## [617] 39.66 330.35 258.62 277.92 4111.40 119.59 434.28
## [624] 316.24 5.48 228.28 265.86 1201.20 102.41 723.10
## [631] 39.47 116.78 121.89 966.10 2365.02 8856.87 384.70
## [638] 279.16 856.28 643.53 494.53 276.79 438.82 489.27
## [645] 1117.11 155.39 487.37 357.90 411.14 141.13 1069.34
## [652] 752.56 12740.80 1592.10 724.17 10042.30 127.56 358.62
## [659] 431.14 1064.83 99.86 509.25 890.84 336.03 548.16
## [666] 948.67 415.63 331.71 113.71 251.39 1492.32 164.80
## [673] 1763.26 31.08 2228.22 356.61 3019.34 241.38 620.70
## [680] 414.28 257.91 1416.17 20.72 639.76 99.74 481.03
## [687] 435.73 184.64 746.46 274.71 415.50 351.06 1170.20
## [694] 4792.16 437.54 29973.60 278.77 713.63 1592.06 550.46
## [701] 157.68 418.13 1223.88 37.94 311.95 2090.93 408.57
## [708] 1135.98 1024.90 427.59 1480.23 6687.72 9218.86 8012.80
## [715] 196567.00 13536.00 131.53 504.52 363.71 628.37 3250.02
## [722] 3604.06 74.73 1281.50 4821.65 3029.73 1839.38 2175.30
## [729] 47680.00 11164.10 339.98 5865.03 1010.50 1548.47 18671.50
## [736] 2519.64 59.25 592.99 918.16 274.50 1765.12 26.02
## [743] 687.27 674.77 1318.01 650.69 1331.52 127.16 629.85
## [750] 945.16 4056.11 3336.95 823.05 3583.08 21.36 289.46
## [757] 2432.00 28827.50 6094.45 276.94 635.57 3947.64 820.82
## [764] 729.14 3067.24 195.49 1935.69 3866.28 3532.11 484.08
## [771] 180.92 1529.05 431.03 642.78 3517.98 8084.37 1292.87
## [778] 4267.76 464.86 2700.90 33865.00 5301.34 96.34 325.71
## [785] 2348.19 801.11 1121.43 2947.72 855.53 2739.30 908.48
## [792] 820.14 1218.25 2401.99 286.60 212.56 2758.33 6505.41
## [799] 855.88 440.68 3860.15 401.15 1609.38 18210.20 2346.63
## [806] 202.12 680.91 548.87 755.80 273.80 385.10 406.02
## [813] 167.01 352.52 412.29 761.27 981.94 207.22 820.07
## [820] 1277.46 273.83
range(qt2_5$Weight) #0.17-196567.00
## [1] 0.17 196567.00
# To-do : normalise the weights to better visualise in graph. Convert to csv maybe.
#any(qt2_6$Target) == any(qt2_6$Source)
Graph 3 Analysis:
library(here)
library(tidyverse)
# Load The Data:
qt3 <- data.table::fread(here::here("data", "Q1-Graph3.csv"))
head(qt3)
## Source eType Target Time Weight SourceLocation TargetLocation
## 1: 614761 4 514306 -209742644 0.1 NA NA
## 2: 614761 1 542965 1672686 1.0 1 2
## 3: 538892 1 572391 1749455 1.0 2 2
## 4: 538892 0 614761 2020424 1.0 NA NA
## 5: 614761 1 500813 2220686 1.0 1 1
## 6: 500813 0 542965 2274331 1.0 NA NA
## SourceLatitude SourceLongitude TargetLatitude TargetLongitude
## 1: NA NA NA NA
## 2: -27.7842 -8.74823 -21.8960 89.4000
## 3: -23.5953 91.35710 -21.1411 91.1427
## 4: NA NA NA NA
## 5: -27.7842 -8.74823 -29.1714 -10.4930
## 6: NA NA NA NA
tail(qt3)
## Source eType Target Time Weight SourceLocation TargetLocation
## 1: 500813 5 644226 31536000 1241.29 NA NA
## 2: 500813 5 632961 31536000 285.60 NA NA
## 3: 500813 5 473173 31536000 1413.05 NA NA
## 4: 500813 5 620120 31536000 2892.02 NA NA
## 5: 500813 5 575030 31536000 7926.69 NA NA
## 6: 500813 5 621924 31536000 930.98 NA NA
## SourceLatitude SourceLongitude TargetLatitude TargetLongitude
## 1: NA NA NA NA
## 2: NA NA NA NA
## 3: NA NA NA NA
## 4: NA NA NA NA
## 5: NA NA NA NA
## 6: NA NA NA NA
# Summarising the Data:
summary(qt3)
## Source eType Target Time
## Min. :464459 Min. :0.000 Min. :459381 Min. :-209742644
## 1st Qu.:516236 1st Qu.:5.000 1st Qu.:520084 1st Qu.: 19884838
## Median :542649 Median :5.000 Median :567195 Median : 31536000
## Mean :549316 Mean :3.981 Mean :556662 Mean : 25673131
## 3rd Qu.:578531 3rd Qu.:5.000 3rd Qu.:595581 3rd Qu.: 31536000
## Max. :657076 Max. :6.000 Max. :657173 Max. : 31536000
##
## Weight SourceLocation TargetLocation SourceLatitude
## Min. : 0.1 Min. :0.000 Min. :0.00 Min. :-29.171
## 1st Qu.: 3.0 1st Qu.:1.000 1st Qu.:1.00 1st Qu.:-25.000
## Median : 507.5 Median :2.000 Median :2.00 Median :-22.000
## Mean : 3726.0 Mean :2.579 Mean :2.25 Mean : -7.727
## 3rd Qu.: 2277.9 3rd Qu.:4.000 3rd Qu.:4.00 3rd Qu.: 2.352
## Max. :159997.0 Max. :5.000 Max. :5.00 Max. : 33.000
## NA's :641 NA's :641 NA's :641
## SourceLongitude TargetLatitude TargetLongitude
## Min. :-165.00 Min. :-29.171 Min. :-165.00
## 1st Qu.:-161.28 1st Qu.:-23.595 1st Qu.:-111.00
## Median : -13.00 Median :-21.141 Median : -26.70
## Mean : -23.88 Mean : -6.860 Mean : -20.84
## 3rd Qu.: 91.00 3rd Qu.: 5.912 3rd Qu.: 91.00
## Max. : 156.00 Max. : 33.574 Max. : 156.00
## NA's :641 NA's :641 NA's :641
nrow(qt3) #729
## [1] 729
ncol(qt3) #11
## [1] 11
qt3$Source <- as.character(qt3$Source)
qt3$Target <- as.character(qt3$Target)
# Differentiating between channels:
qt3_01 <- qt3 %>% filter(qt3$eType == 0 | qt3$eType == 1) # Communication Channel
nrow(qt3_01) # 160
## [1] 160
qt3_23 <- qt3 %>% filter(qt3$eType == 2 | qt3$eType == 3) # Procurement Channel
nrow(qt3_23) # 12
## [1] 12
qt3_4 <- qt3 %>% filter(qt3$eType == 4) # Co-authorship Channel
nrow(qt3_4) # 1
## [1] 1
qt3_5 <- qt3 %>% filter(qt3$eType == 5) # Demographic Channel
nrow(qt3_5) # 519
## [1] 519
qt3_6 <- qt3 %>% filter(qt3$eType == 6) # Travel Channel
nrow(qt3_6) # 37
## [1] 37
# Highest data for Demographic, Communication and Travel Channel.
# Analysis of the Communication channel:
glimpse(qt3_01)
## Observations: 160
## Variables: 11
## $ Source <chr> "614761", "538892", "538892", "614761", "50081...
## $ eType <int> 1, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1...
## $ Target <chr> "542965", "572391", "614761", "500813", "54296...
## $ Time <int> 1672686, 1749455, 2020424, 2220686, 2274331, 2...
## $ Weight <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1...
## $ SourceLocation <int> 1, 2, NA, 1, NA, NA, NA, 1, NA, 1, 1, NA, 2, 1...
## $ TargetLocation <int> 2, 2, NA, 1, NA, NA, NA, 2, NA, 1, 1, NA, 1, 2...
## $ SourceLatitude <dbl> -27.7842, -23.5953, NA, -27.7842, NA, NA, NA, ...
## $ SourceLongitude <dbl> -8.74823, 91.35710, NA, -8.74823, NA, NA, NA, ...
## $ TargetLatitude <dbl> -21.8960, -21.1411, NA, -29.1714, NA, NA, NA, ...
## $ TargetLongitude <dbl> 89.40000, 91.14270, NA, -10.49300, NA, NA, NA,...
#unique(qt3_01)
unique(qt3_01$eType) # 0 1
## [1] 1 0
unique(qt3_01$SourceLocation) # 1 2 NA 4 5 0
## [1] 1 2 NA 4 5 0
unique(qt3_01$TargetLocation) # 2 NA 1 0 4 5
## [1] 2 NA 1 0 4 5
unique(qt3_01$SourceLatitude) # -27.78420 -23.59530 NA -29.17140 5.91178 24.98310 32.11920 2.35166
## [1] -27.78420 -23.59530 NA -29.17140 5.91178 24.98310 32.11920
## [8] 2.35166
unique(qt3_01$SourceLongitude)# -8.74823 91.35710 NA -10.49300 -161.27600 155.44600 -47.35310 -161.32200
## [1] -8.74823 91.35710 NA -10.49300 -161.27600 155.44600
## [7] -47.35310 -161.32200
unique(qt3_01$TargetLatitude) # -21.89600 -21.14110 NA -29.17140 -27.78420 -23.59530 33.57410 2.35166 32.11920 24.98310 5.91178
## [1] -21.89600 -21.14110 NA -29.17140 -27.78420 -23.59530 33.57410
## [8] 2.35166 32.11920 24.98310 5.91178
unique(qt3_01$TargetLongitude) # 89.40000 91.14270 NA -10.49300 -8.74823 91.35710 -40.39040 -161.32200 -47.35310 155.44600 -161.27600
## [1] 89.40000 91.14270 NA -10.49300 -8.74823 91.35710
## [7] -40.39040 -161.32200 -47.35310 155.44600 -161.27600
unique(qt3_01$Source)
## [1] "614761" "538892" "500813" "493094" "536003" "521318" "542649"
## [8] "572391" "541619" "544074" "493652" "516236" "607386"
unique(qt3_01$Target)
## [1] "542965" "572391" "614761" "500813" "538892" "493094" "536003"
## [8] "521318" "607386" "516236" "493652" "542649" "544074" "541619"
colnames(qt3_01)
## [1] "Source" "eType" "Target"
## [4] "Time" "Weight" "SourceLocation"
## [7] "TargetLocation" "SourceLatitude" "SourceLongitude"
## [10] "TargetLatitude" "TargetLongitude"
# Analysis of the Demographic channel:
glimpse(qt3_5)
## Observations: 519
## Variables: 11
## $ Source <chr> "610497", "610497", "552988", "610497", "61049...
## $ eType <int> 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5...
## $ Target <chr> "640784", "630626", "610497", "567195", "52744...
## $ Time <int> 31536000, 31536000, 31536000, 31536000, 315360...
## $ Weight <dbl> 271.92, 961.13, 3704.63, 2020.36, 164.35, 516....
## $ SourceLocation <int> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLocation <int> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ SourceLatitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ SourceLongitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLatitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLongitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
#unique(qt3_5)
unique(qt3_5$eType) # 5
## [1] 5
unique(qt3_5$SourceLocation) # NA
## [1] NA
unique(qt3_5$TargetLocation) # NA
## [1] NA
unique(qt3_5$SourceLatitude) # NA
## [1] NA
unique(qt3_5$SourceLongitude) # NA
## [1] NA
unique(qt3_5$TargetLatitude) # NA
## [1] NA
unique(qt3_5$TargetLongitude) # NA
## [1] NA
unique(qt3_5$Source)
## [1] "610497" "552988" "578531" "510031" "657076" "478754" "575295"
## [8] "568284" "508898" "538892" "620120" "572391" "542965" "536951"
## [15] "466976" "607386" "628223" "516236" "492701" "584736" "520084"
## [22] "529433" "493094" "604113" "493652" "544074" "541619" "614761"
## [29] "500813"
unique(qt3_5$Target)
## [1] "640784" "630626" "610497" "567195" "527449" "459381" "595298"
## [8] "466907" "589943" "537281" "523927" "580426" "616315" "503701"
## [15] "632961" "473173" "620120" "575030" "503218" "578531" "606730"
## [22] "577992" "642329" "621924" "657076" "478754" "571970" "575295"
## [29] "595581" "568284" "508898" "538892" "572391" "542965" "536951"
## [36] "466976" "607386" "628223" "516236" "536346" "520660" "492701"
## [43] "644226" "584736" "520084" "529433" "493094" "604113" "493652"
## [50] "544074" "541619" "614761" "500813"
unique(qt3_5$Weight)
## [1] 271.92 961.13 3704.63 2020.36 164.35 516.88 707.62
## [8] 382.90 299.92 476.32 191.06 180.33 365.16 1626.32
## [15] 196.78 91.95 119.20 3200.70 127.15 794.95 5216.01
## [22] 535.49 44432.60 4032.44 112.79 564.37 3687.96 604.91
## [29] 1122.89 1464.95 4967.63 951.82 1875.25 765.20 94.12
## [36] 842.49 2131.32 779.39 979.19 6814.56 3994.14 1367.71
## [43] 983.51 4887.83 36157.50 384.30 595.71 2596.98 458.72
## [50] 1950.69 530.82 1922.91 501.28 1384.47 719.92 180.60
## [57] 242.37 5823.53 7256.03 1257.76 6376.02 197.45 29465.30
## [64] 334.00 546.44 1567.57 1232.64 1763.76 179.32 904.42
## [71] 671.78 885.78 132.51 105.23 2312.74 2277.90 611.39
## [78] 1131.09 25163.80 516.47 173.64 1609.94 429.42 2117.18
## [85] 277.44 1211.81 1191.34 2.91 280.94 60.24 281.97
## [92] 2150.02 1213.18 5529.22 1638.18 5053.94 7039.65 1147.37
## [99] 285.70 267.45 3054.32 701.36 369.91 279.83 141.32
## [106] 584.34 1772.19 955.54 818.09 2456.28 92.37 439.20
## [113] 3084.78 164.30 3861.34 817.27 1437.55 7216.68 2664.62
## [120] 50214.10 5377.20 73.45 624.98 2939.52 1068.85 2951.76
## [127] 1414.30 3035.49 384.00 1272.62 187.12 3744.72 1245.58
## [134] 13481.80 19974.00 1053.33 612.53 7866.03 804.60 66.56
## [141] 206.85 2929.23 411.67 1336.50 2087.94 115.09 318.53
## [148] 287.96 1700.68 232.76 397.53 1256.32 2011.04 7084.51
## [155] 323.44 9063.18 593.37 377.58 330.92 642.73 288.38
## [162] 1117.58 619.38 315.44 140.14 253.64 1960.88 214.29
## [169] 787.03 1472.17 7690.99 3433.52 14865.80 1031.52 149.53
## [176] 737.83 3375.37 177.36 232.68 136.94 1100.57 613.80
## [183] 1637.51 1420.57 415.80 210.09 373.32 310.96 804.21
## [190] 8413.60 798.15 1252.81 5234.64 4019.67 507.47 200.63
## [197] 1391.04 620.27 449.32 2552.28 421.71 475.36 394.63
## [204] 954.38 2141.56 1414.94 3296.54 221.54 1187.43 4620.27
## [211] 38019.80 640.95 2249.28 7533.16 576.32 3435.72 3963.81
## [218] 848.82 3202.79 1652.08 5169.73 168.32 723.89 7146.89
## [225] 248.90 5749.62 3816.99 915.56 67455.80 3985.69 352.43
## [232] 174.81 5638.62 2396.91 622.79 170.71 4129.17 790.97
## [239] 618.59 2377.76 6084.53 347.93 3632.97 601.22 18698.10
## [246] 2016.27 2582.67 8091.25 1129.49 86251.60 9336.13 576.14
## [253] 978.47 8384.06 1096.37 1846.53 948.57 4632.30 30.83
## [260] 3739.59 4394.98 7443.20 304.78 520.28 6636.04 4485.42
## [267] 19153.40 1117.73 39291.80 6908.27 159997.00 32142.30 713.06
## [274] 1904.74 1406.81 1929.22 6938.77 5302.10 2618.50 8956.10
## [281] 11185.40 4836.31 2574.66 280.38 353.31 2489.02 146800.00
## [288] 41464.40 47400.00 1399.05 9335.04 6111.55 4744.49 39167.10
## [295] 170.12 1819.60 8665.54 1433.99 4463.25 2261.47 3006.51
## [302] 3052.63 2193.96 251.90 2367.25 532.37 612.60 4436.30
## [309] 16279.80 19167.70 134196.00 26846.90 494.71 2778.19 7045.08
## [316] 534.07 12526.90 6214.69 1500.31 15399.50 535.85 6650.38
## [323] 5190.51 117.94 1100.50 8001.41 11520.60 15668.20 1761.31
## [330] 10072.20 3978.84 2024.70 11179.50 129601.00 17907.00 522.39
## [337] 994.25 2315.62 1531.51 15080.30 8845.36 2262.18 5343.67
## [344] 2588.29 13260.70 2230.88 16249.60 2347.91 2580.06 530.03
## [351] 20358.50 30415.80 3538.33 13854.70 4349.74 1284.37 10862.70
## [358] 121408.00 6540.34 1415.99 1597.54 1812.17 2716.27 3419.82
## [365] 3143.13 8060.60 460.34 5167.03 2514.63 4385.38 684.27
## [372] 210.50 2158.60 1017.67 6453.51 13393.60 15821.90 6900.20
## [379] 10157.60 79413.80 6315.32 1159.64 1793.02 2799.86 1723.73
## [386] 4391.21 78.87 10214.80 1173.68 1631.93 4803.92 3163.52
## [393] 616.21 3725.96 3582.65 2441.93 115.29 2933.47 102.25
## [400] 153.88 698.03 926.20 233.46 539.30 323.11 53.94
## [407] 437.88 402.74 449.99 1.53 435.11 154.55 796.54
## [414] 735.72 15445.80 2055.58 142.76 156.76 1299.03 336.29
## [421] 120.27 304.65 1011.58 214.43 284.93 490.95 1132.00
## [428] 38.67 78.12 1651.44 1018.22 8492.89 85.67 173.45
## [435] 5639.96 1003.13 139.33 259.10 370.86 132.61 233.70
## [442] 73.43 114.21 382.88 18.12 376.40 447.16 567.43
## [449] 4.52 592.22 243.68 2345.31 1088.77 444.32 713.50
## [456] 4553.79 26.11 75.27 218.46 208.62 231.44 577.37
## [463] 16.34 92.30 263.52 125.82 588.78 669.26 21.65
## [470] 574.32 4.93 146.40 85.13 1085.42 72.99 2793.29
## [477] 283.97 4471.64 2505.35 24662.90 11.82 663.33 1026.74
## [484] 584.32 847.85 425.54 3508.30 17.14 460.73 532.11
## [491] 1698.46 489.33 2501.87 2556.09 5740.10 185.98 3233.06
## [498] 1861.41 1208.09 26707.80 3517.64 162.65 340.32 703.66
## [505] 243.26 2066.72 635.44 2511.22 249.16 708.12 1122.43
## [512] 1552.37 161.16 1241.29 285.60 1413.05 2892.02 7926.69
## [519] 930.98
qt3_5 <- subset(qt3_5, select = -c(SourceLocation, TargetLocation, SourceLatitude, SourceLongitude, TargetLatitude, TargetLongitude)) # SOurce and Target Latitude and Longitude columns removed as all Null.
colnames(qt3_5)
## [1] "Source" "eType" "Target" "Time" "Weight"
range(qt3_5$Source) # 466976 657076
## [1] "466976" "657076"
range(qt3_5$Target) # 459381 657076
## [1] "459381" "657076"
range(qt3_5$Time) # 31536000-31536000
## [1] 31536000 31536000
income_cat_qt3 <- NULL
# Income Categories:
for (i in (qt3_5$Source)) {
for (j in (cat$NodeID)) { # cat_list contains all the demographic nodeIDs (from the DemographicNodeExtraction Script)
if(i == j){
income_cat_qt3 <- append(income_cat_qt3,i)
}
}
}
print(income_cat_qt3) # income categories extracted
## [1] "552988" "510031" "552988" "552988" "510031" "552988" "552988"
## [8] "552988" "510031" "552988" "510031" "552988" "620120" "510031"
## [15] "552988" "620120" "552988" "552988" "552988" "510031" "552988"
## [22] "620120" "510031" "552988" "510031" "552988" "552988" "552988"
## [29] "510031" "552988" "510031" "552988" "552988" "510031" "552988"
## [36] "620120" "510031" "552988" "510031" "552988" "552988" "510031"
## [43] "552988" "552988"
unique(income_cat_qt3) # 3
## [1] "552988" "510031" "620120"
qt3_5_sub1 <- subset(qt3_5, qt3_5$Source == income_cat_qt3) # Subset of data with only income categories
## Warning in qt3_5$Source == income_cat_qt3: longer object length is not a
## multiple of shorter object length
str(qt3_5_sub1)
## 'data.frame': 25 obs. of 5 variables:
## $ Source: chr "552988" "552988" "552988" "552988" ...
## $ eType : int 5 5 5 5 5 5 5 5 5 5 ...
## $ Target: chr "610497" "657076" "478754" "575295" ...
## $ Time : int 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 ...
## $ Weight: num 3705 36158 29465 25164 2665 ...
plot(qt3_5_sub1$Source, qt3_5_sub1$Weight) # Plot of Monetary income in each category
# Expense Categories:
expense_cat_qt3 <- NULL
for (k in qt3_5$Target) {
for(l in cat$NodeID){
if(k==l){
expense_cat_qt3 <- append(expense_cat_qt3, k)
}
}
}
print(expense_cat_qt3) # expense categories extracted
## [1] "640784" "630626" "567195" "527449" "459381" "595298" "466907"
## [8] "589943" "537281" "523927" "580426" "616315" "503701" "632961"
## [15] "473173" "620120" "575030" "640784" "503218" "630626" "567195"
## [22] "527449" "459381" "595298" "466907" "606730" "589943" "577992"
## [29] "537281" "523927" "580426" "616315" "642329" "503701" "632961"
## [36] "473173" "620120" "575030" "621924" "640784" "630626" "527449"
## [43] "459381" "595298" "466907" "589943" "537281" "523927" "580426"
## [50] "616315" "642329" "503701" "473173" "620120" "575030" "621924"
## [57] "630626" "527449" "459381" "595298" "466907" "589943" "577992"
## [64] "523927" "616315" "642329" "571970" "632961" "473173" "620120"
## [71] "621924" "630626" "527449" "459381" "595298" "466907" "577992"
## [78] "537281" "523927" "595581" "616315" "642329" "571970" "632961"
## [85] "473173" "620120" "575030" "621924" "630626" "567195" "527449"
## [92] "459381" "595298" "466907" "589943" "577992" "537281" "523927"
## [99] "595581" "616315" "642329" "503701" "571970" "632961" "473173"
## [106] "620120" "575030" "621924" "503218" "630626" "567195" "527449"
## [113] "459381" "595298" "466907" "589943" "537281" "523927" "580426"
## [120] "595581" "642329" "503701" "473173" "620120" "575030" "621924"
## [127] "567195" "527449" "459381" "595298" "466907" "589943" "577992"
## [134] "537281" "523927" "580426" "642329" "632961" "473173" "575030"
## [141] "621924" "567195" "527449" "459381" "595298" "466907" "589943"
## [148] "577992" "537281" "580426" "616315" "503701" "632961" "473173"
## [155] "575030" "621924" "567195" "527449" "459381" "595298" "466907"
## [162] "589943" "537281" "523927" "580426" "595581" "616315" "642329"
## [169] "571970" "632961" "473173" "620120" "575030" "621924" "503218"
## [176] "567195" "527449" "459381" "595298" "466907" "589943" "577992"
## [183] "537281" "523927" "580426" "595581" "616315" "642329" "503701"
## [190] "473173" "620120" "575030" "527449" "459381" "595298" "466907"
## [197] "589943" "577992" "537281" "523927" "642329" "503701" "571970"
## [204] "632961" "473173" "620120" "575030" "621924" "567195" "527449"
## [211] "459381" "595298" "466907" "589943" "537281" "523927" "580426"
## [218] "595581" "642329" "503701" "632961" "473173" "575030" "621924"
## [225] "503218" "630626" "567195" "527449" "459381" "595298" "466907"
## [232] "606730" "537281" "523927" "580426" "595581" "642329" "503701"
## [239] "571970" "632961" "473173" "620120" "575030" "621924" "630626"
## [246] "567195" "527449" "459381" "595298" "466907" "589943" "537281"
## [253] "523927" "580426" "595581" "616315" "503701" "571970" "632961"
## [260] "473173" "620120" "575030" "621924" "503218" "630626" "536346"
## [267] "520660" "527449" "459381" "595298" "466907" "589943" "523927"
## [274] "595581" "616315" "642329" "571970" "644226" "632961" "473173"
## [281] "620120" "575030" "630626" "567195" "527449" "459381" "595298"
## [288] "466907" "589943" "523927" "580426" "595581" "616315" "642329"
## [295] "503701" "571970" "632961" "473173" "620120" "621924" "640784"
## [302] "630626" "536346" "520660" "567195" "527449" "459381" "595298"
## [309] "466907" "589943" "577992" "537281" "523927" "580426" "595581"
## [316] "642329" "503701" "644226" "632961" "473173" "620120" "575030"
## [323] "640784" "630626" "536346" "520660" "567195" "527449" "459381"
## [330] "595298" "466907" "606730" "589943" "577992" "537281" "523927"
## [337] "580426" "616315" "642329" "503701" "644226" "632961" "473173"
## [344] "620120" "575030" "621924" "630626" "567195" "527449" "459381"
## [351] "595298" "466907" "589943" "577992" "523927" "580426" "616315"
## [358] "642329" "503701" "571970" "473173" "620120" "621924" "567195"
## [365] "527449" "459381" "595298" "466907" "537281" "523927" "580426"
## [372] "616315" "642329" "503701" "632961" "473173" "621924" "567195"
## [379] "527449" "459381" "595298" "466907" "577992" "537281" "523927"
## [386] "595581" "616315" "642329" "503701" "571970" "632961" "473173"
## [393] "620120" "575030" "621924" "567195" "527449" "459381" "595298"
## [400] "466907" "589943" "577992" "537281" "523927" "580426" "595581"
## [407] "616315" "503701" "632961" "473173" "620120" "575030" "630626"
## [414] "536346" "520660" "567195" "527449" "459381" "595298" "466907"
## [421] "589943" "577992" "537281" "523927" "580426" "595581" "616315"
## [428] "642329" "503701" "571970" "644226" "632961" "473173" "620120"
## [435] "575030" "621924" "630626" "527449" "459381" "595298" "466907"
## [442] "577992" "537281" "523927" "580426" "616315" "642329" "503701"
## [449] "632961" "473173" "620120" "575030" "640784" "630626" "536346"
## [456] "520660" "567195" "527449" "459381" "595298" "466907" "577992"
## [463] "537281" "523927" "580426" "616315" "642329" "503701" "571970"
## [470] "644226" "632961" "473173" "620120" "575030" "621924"
unique(expense_cat_qt3) # 27
## [1] "640784" "630626" "567195" "527449" "459381" "595298" "466907"
## [8] "589943" "537281" "523927" "580426" "616315" "503701" "632961"
## [15] "473173" "620120" "575030" "503218" "606730" "577992" "642329"
## [22] "621924" "571970" "595581" "536346" "520660" "644226"
qt3_5_sub2 <- subset(qt3_5, qt3_5$Target == expense_cat_qt3) # Subset of data with only expense categories
## Warning in qt3_5$Target == expense_cat_qt3: longer object length is not a
## multiple of shorter object length
str(qt3_5_sub2)
## 'data.frame': 29 obs. of 5 variables:
## $ Source: chr "610497" "610497" "572391" "572391" ...
## $ eType : int 5 5 5 5 5 5 5 5 5 5 ...
## $ Target: chr "640784" "630626" "567195" "527449" ...
## $ Time : int 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 ...
## $ Weight: num 272 961 593 378 331 ...
plot(qt3_5_sub2$Target, qt3_5_sub2$Weight) # Plot of Monetary expenses in each category
hist(qt3_5$Weight)
unique(qt3_5$Weight)
## [1] 271.92 961.13 3704.63 2020.36 164.35 516.88 707.62
## [8] 382.90 299.92 476.32 191.06 180.33 365.16 1626.32
## [15] 196.78 91.95 119.20 3200.70 127.15 794.95 5216.01
## [22] 535.49 44432.60 4032.44 112.79 564.37 3687.96 604.91
## [29] 1122.89 1464.95 4967.63 951.82 1875.25 765.20 94.12
## [36] 842.49 2131.32 779.39 979.19 6814.56 3994.14 1367.71
## [43] 983.51 4887.83 36157.50 384.30 595.71 2596.98 458.72
## [50] 1950.69 530.82 1922.91 501.28 1384.47 719.92 180.60
## [57] 242.37 5823.53 7256.03 1257.76 6376.02 197.45 29465.30
## [64] 334.00 546.44 1567.57 1232.64 1763.76 179.32 904.42
## [71] 671.78 885.78 132.51 105.23 2312.74 2277.90 611.39
## [78] 1131.09 25163.80 516.47 173.64 1609.94 429.42 2117.18
## [85] 277.44 1211.81 1191.34 2.91 280.94 60.24 281.97
## [92] 2150.02 1213.18 5529.22 1638.18 5053.94 7039.65 1147.37
## [99] 285.70 267.45 3054.32 701.36 369.91 279.83 141.32
## [106] 584.34 1772.19 955.54 818.09 2456.28 92.37 439.20
## [113] 3084.78 164.30 3861.34 817.27 1437.55 7216.68 2664.62
## [120] 50214.10 5377.20 73.45 624.98 2939.52 1068.85 2951.76
## [127] 1414.30 3035.49 384.00 1272.62 187.12 3744.72 1245.58
## [134] 13481.80 19974.00 1053.33 612.53 7866.03 804.60 66.56
## [141] 206.85 2929.23 411.67 1336.50 2087.94 115.09 318.53
## [148] 287.96 1700.68 232.76 397.53 1256.32 2011.04 7084.51
## [155] 323.44 9063.18 593.37 377.58 330.92 642.73 288.38
## [162] 1117.58 619.38 315.44 140.14 253.64 1960.88 214.29
## [169] 787.03 1472.17 7690.99 3433.52 14865.80 1031.52 149.53
## [176] 737.83 3375.37 177.36 232.68 136.94 1100.57 613.80
## [183] 1637.51 1420.57 415.80 210.09 373.32 310.96 804.21
## [190] 8413.60 798.15 1252.81 5234.64 4019.67 507.47 200.63
## [197] 1391.04 620.27 449.32 2552.28 421.71 475.36 394.63
## [204] 954.38 2141.56 1414.94 3296.54 221.54 1187.43 4620.27
## [211] 38019.80 640.95 2249.28 7533.16 576.32 3435.72 3963.81
## [218] 848.82 3202.79 1652.08 5169.73 168.32 723.89 7146.89
## [225] 248.90 5749.62 3816.99 915.56 67455.80 3985.69 352.43
## [232] 174.81 5638.62 2396.91 622.79 170.71 4129.17 790.97
## [239] 618.59 2377.76 6084.53 347.93 3632.97 601.22 18698.10
## [246] 2016.27 2582.67 8091.25 1129.49 86251.60 9336.13 576.14
## [253] 978.47 8384.06 1096.37 1846.53 948.57 4632.30 30.83
## [260] 3739.59 4394.98 7443.20 304.78 520.28 6636.04 4485.42
## [267] 19153.40 1117.73 39291.80 6908.27 159997.00 32142.30 713.06
## [274] 1904.74 1406.81 1929.22 6938.77 5302.10 2618.50 8956.10
## [281] 11185.40 4836.31 2574.66 280.38 353.31 2489.02 146800.00
## [288] 41464.40 47400.00 1399.05 9335.04 6111.55 4744.49 39167.10
## [295] 170.12 1819.60 8665.54 1433.99 4463.25 2261.47 3006.51
## [302] 3052.63 2193.96 251.90 2367.25 532.37 612.60 4436.30
## [309] 16279.80 19167.70 134196.00 26846.90 494.71 2778.19 7045.08
## [316] 534.07 12526.90 6214.69 1500.31 15399.50 535.85 6650.38
## [323] 5190.51 117.94 1100.50 8001.41 11520.60 15668.20 1761.31
## [330] 10072.20 3978.84 2024.70 11179.50 129601.00 17907.00 522.39
## [337] 994.25 2315.62 1531.51 15080.30 8845.36 2262.18 5343.67
## [344] 2588.29 13260.70 2230.88 16249.60 2347.91 2580.06 530.03
## [351] 20358.50 30415.80 3538.33 13854.70 4349.74 1284.37 10862.70
## [358] 121408.00 6540.34 1415.99 1597.54 1812.17 2716.27 3419.82
## [365] 3143.13 8060.60 460.34 5167.03 2514.63 4385.38 684.27
## [372] 210.50 2158.60 1017.67 6453.51 13393.60 15821.90 6900.20
## [379] 10157.60 79413.80 6315.32 1159.64 1793.02 2799.86 1723.73
## [386] 4391.21 78.87 10214.80 1173.68 1631.93 4803.92 3163.52
## [393] 616.21 3725.96 3582.65 2441.93 115.29 2933.47 102.25
## [400] 153.88 698.03 926.20 233.46 539.30 323.11 53.94
## [407] 437.88 402.74 449.99 1.53 435.11 154.55 796.54
## [414] 735.72 15445.80 2055.58 142.76 156.76 1299.03 336.29
## [421] 120.27 304.65 1011.58 214.43 284.93 490.95 1132.00
## [428] 38.67 78.12 1651.44 1018.22 8492.89 85.67 173.45
## [435] 5639.96 1003.13 139.33 259.10 370.86 132.61 233.70
## [442] 73.43 114.21 382.88 18.12 376.40 447.16 567.43
## [449] 4.52 592.22 243.68 2345.31 1088.77 444.32 713.50
## [456] 4553.79 26.11 75.27 218.46 208.62 231.44 577.37
## [463] 16.34 92.30 263.52 125.82 588.78 669.26 21.65
## [470] 574.32 4.93 146.40 85.13 1085.42 72.99 2793.29
## [477] 283.97 4471.64 2505.35 24662.90 11.82 663.33 1026.74
## [484] 584.32 847.85 425.54 3508.30 17.14 460.73 532.11
## [491] 1698.46 489.33 2501.87 2556.09 5740.10 185.98 3233.06
## [498] 1861.41 1208.09 26707.80 3517.64 162.65 340.32 703.66
## [505] 243.26 2066.72 635.44 2511.22 249.16 708.12 1122.43
## [512] 1552.37 161.16 1241.29 285.60 1413.05 2892.02 7926.69
## [519] 930.98
range(qt3_5$Weight) #1.53 159997.00
## [1] 1.53 159997.00
# To-do : normalise the weights to better visualise in graph. Convert to csv maybe.
Graph 4 Analysis:
# Load The Data:
qt4 <- data.table::fread(here::here("data", "Q1-Graph4.csv"))
head(qt4)
## Source eType Target Time Weight SourceLocation TargetLocation
## 1: 636721 2 585417 98586 1398 NA NA
## 2: 628320 1 557269 186326 1 4 4
## 3: 546593 1 492850 211842 1 0 3
## 4: 536906 0 569329 925206 1 NA NA
## 5: 483005 0 655963 1214644 1 NA NA
## 6: 601496 0 557269 1233608 1 NA NA
## SourceLatitude SourceLongitude TargetLatitude TargetLongitude
## 1: NA NA NA NA
## 2: 0.224078 -163.6240 2.40053 -161.288
## 3: 32.214600 -42.6609 -24.99040 -111.346
## 4: NA NA NA NA
## 5: NA NA NA NA
## 6: NA NA NA NA
tail(qt4)
## Source eType Target Time Weight SourceLocation TargetLocation
## 1: 541907 5 503701 31536000 435.81 NA NA
## 2: 541907 5 632961 31536000 114.54 NA NA
## 3: 541907 5 473173 31536000 43.82 NA NA
## 4: 510031 5 541907 31536000 357.94 NA NA
## 5: 552988 5 541907 31536000 7219.68 NA NA
## 6: 620120 5 541907 31536000 7.79 NA NA
## SourceLatitude SourceLongitude TargetLatitude TargetLongitude
## 1: NA NA NA NA
## 2: NA NA NA NA
## 3: NA NA NA NA
## 4: NA NA NA NA
## 5: NA NA NA NA
## 6: NA NA NA NA
# Summarising the Data:
summary(qt4)
## Source eType Target Time
## Min. :464579 Min. :0.000 Min. :459381 Min. : 98586
## 1st Qu.:510031 1st Qu.:5.000 1st Qu.:527449 1st Qu.:26425410
## Median :566580 Median :5.000 Median :577992 Median :31536000
## Mean :557659 Mean :4.463 Mean :568697 Mean :26478065
## 3rd Qu.:585606 3rd Qu.:5.000 3rd Qu.:620120 3rd Qu.:31536000
## Max. :657526 Max. :6.000 Max. :657526 Max. :31536000
##
## Weight SourceLocation TargetLocation SourceLatitude
## Min. : -1.0 Min. :0.000 Min. :0.000 Min. :-29.676
## 1st Qu.: 3.0 1st Qu.:0.000 1st Qu.:1.000 1st Qu.:-24.993
## Median : 337.5 Median :2.000 Median :3.000 Median : 2.401
## Mean : 2154.4 Mean :2.085 Mean :2.534 Mean : 3.742
## 3rd Qu.: 1370.2 3rd Qu.:3.250 3rd Qu.:4.000 3rd Qu.: 33.000
## Max. :141744.0 Max. :5.000 Max. :5.000 Max. : 39.889
## NA's :556 NA's :556 NA's :556
## SourceLongitude TargetLatitude TargetLongitude
## Min. :-165.00 Min. :-35.6034 Min. :-168.96
## 1st Qu.:-111.00 1st Qu.:-25.0000 1st Qu.:-111.00
## Median : -41.00 Median : 1.0000 Median : -41.78
## Mean : -23.21 Mean : 0.5186 Mean : -35.92
## 3rd Qu.: 91.00 3rd Qu.: 22.1073 3rd Qu.: -11.44
## Max. : 156.00 Max. : 39.8886 Max. : 156.26
## NA's :556 NA's :556 NA's :556
nrow(qt4) #732
## [1] 732
ncol(qt4) #11
## [1] 11
qt4$Source <- as.character(qt4$Source)
qt4$Target <- as.character(qt4$Target)
# Differentiating between channels:
qt4_01 <- qt4 %>% filter(qt4$eType == 0 | qt4$eType == 1) # Communication Channel
nrow(qt4_01) # 106
## [1] 106
qt4_23 <- qt4 %>% filter(qt4$eType == 2 | qt4$eType == 3) # Procurement Channel
nrow(qt4_23) # 17
## [1] 17
qt4_4 <- qt4 %>% filter(qt4$eType == 4) # Co-authorship Channel
nrow(qt4_4) # 0
## [1] 0
qt4_5 <- qt4 %>% filter(qt4$eType == 5) # Demographic Channel
nrow(qt4_5) # 494
## [1] 494
qt4_6 <- qt4 %>% filter(qt4$eType == 6) # Travel Channel
nrow(qt4_6) # 115
## [1] 115
# Highest data for Demographic, Communication and Travel Channel.
# Analysis of the Communication channel:
glimpse(qt4_01)
## Observations: 106
## Variables: 11
## $ Source <chr> "628320", "546593", "536906", "483005", "60149...
## $ eType <int> 1, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 1, 1, 0, 0...
## $ Target <chr> "557269", "492850", "569329", "655963", "55726...
## $ Time <int> 186326, 211842, 925206, 1214644, 1233608, 1648...
## $ Weight <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1...
## $ SourceLocation <int> 4, 0, NA, NA, NA, 5, 4, 0, NA, NA, NA, NA, 0, ...
## $ TargetLocation <int> 4, 3, NA, NA, NA, 5, 3, 3, NA, NA, NA, NA, 3, ...
## $ SourceLatitude <dbl> 0.224078, 32.214600, NA, NA, NA, 21.543400, 2....
## $ SourceLongitude <dbl> -163.6240, -42.6609, NA, NA, NA, 154.2790, -16...
## $ TargetLatitude <dbl> 2.40053, -24.99040, NA, NA, NA, 21.54340, -23....
## $ TargetLongitude <dbl> -161.288, -111.346, NA, NA, NA, 154.279, -111....
#unique(qt4_01)
unique(qt4_01$eType) # 0 1
## [1] 1 0
unique(qt4_01$SourceLocation) # 4 0 NA 5 1 3
## [1] 4 0 NA 5 1 3
unique(qt4_01$TargetLocation) # 4 3 NA 5 2 1 0
## [1] 4 3 NA 5 2 1 0
unique(qt4_01$SourceLatitude)
## [1] 0.224078 32.214600 NA 21.543400 2.400530 39.888600
## [7] 28.742600 22.429000 33.783300 -25.732900 -23.875500 3.004860
## [13] -25.232400 -29.676400 29.416200 -24.475000 -24.990400 -24.575600
## [19] 19.138600
unique(qt4_01$SourceLongitude)
## [1] -163.6240 -42.6609 NA 154.2790 -161.2880 -41.7780 -41.4508
## [8] 154.8590 -45.4927 -14.9697 -111.5410 -159.2300 -110.1800 -11.6307
## [15] -45.8675 -111.1470 -111.3460 -110.9450 155.0990
unique(qt4_01$TargetLatitude)
## [1] 2.400530 -24.990400 NA 21.543400 -23.875500 -24.575600
## [7] 3.004860 -22.066000 -32.706500 22.429000 39.888600 0.224078
## [13] -25.178100 28.742600 29.416200 -24.475000 -24.037600 -21.154500
## [19] -35.603400 -24.929700 5.330310 20.783900 -24.066100 20.100500
## [25] 33.783300 -27.058200 39.457100 -24.374800 -25.232400 -3.350860
unique(qt4_01$TargetLongitude)
## [1] -161.2880 -111.3460 NA 154.2790 -111.5410 -110.9450 -159.2300
## [8] 93.1290 -10.3259 154.8590 -41.7780 -163.6240 -110.1440 -41.4508
## [15] -45.8675 -111.1470 -110.7300 88.0749 -11.7988 -111.0140 -168.9570
## [22] 156.2560 -111.9360 154.0040 -45.4927 -10.3526 -48.4240 -111.2570
## [29] -110.1800 -162.1800
unique(qt4_01$Source)
## [1] "628320" "546593" "536906" "483005" "601496" "639642" "557269"
## [8] "579305" "584457" "516873" "492850" "569329" "544636" "580798"
## [15] "464579" "636721" "566580" "657526" "588172" "585606" "655963"
## [22] "541907" "482012"
unique(qt4_01$Target)
## [1] "557269" "492850" "569329" "655963" "639642" "544636" "483005"
## [8] "580798" "584457" "482012" "541907" "611572" "601496" "588172"
## [15] "546593" "516873" "585606" "580237" "536906" "579305" "628320"
## [22] "571369" "596726" "537816" "657526" "464579" "558089" "459726"
## [29] "578749" "571670" "500336" "566580" "636721" "623468" "477374"
## [36] "611238" "521673" "516393" "645371"
colnames(qt4_01)
## [1] "Source" "eType" "Target"
## [4] "Time" "Weight" "SourceLocation"
## [7] "TargetLocation" "SourceLatitude" "SourceLongitude"
## [10] "TargetLatitude" "TargetLongitude"
# Analysis of the Demographic channel:
glimpse(qt4_5)
## Observations: 494
## Variables: 11
## $ Source <chr> "464579", "464579", "464579", "464579", "46457...
## $ eType <int> 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5...
## $ Target <chr> "536346", "567195", "527449", "459381", "59529...
## $ Time <int> 31536000, 31536000, 31536000, 31536000, 315360...
## $ Weight <dbl> 5352.39, 1900.95, 1574.64, 1363.77, 9000.70, 1...
## $ SourceLocation <int> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLocation <int> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ SourceLatitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ SourceLongitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLatitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLongitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
#unique(qt4_5)
unique(qt4_5$eType) # 5
## [1] 5
unique(qt4_5$SourceLocation) # NA
## [1] NA
unique(qt4_5$TargetLocation) # NA
## [1] NA
unique(qt4_5$SourceLatitude) # NA
## [1] NA
unique(qt4_5$SourceLongitude) # NA
## [1] NA
unique(qt4_5$TargetLatitude) # NA
## [1] NA
unique(qt4_5$TargetLongitude) # NA
## [1] NA
unique(qt4_5$Source)
## [1] "464579" "482012" "492850" "510031" "536906" "546593" "552988"
## [8] "569329" "580798" "588172" "620120" "636721" "657526" "557269"
## [15] "655963" "639642" "585606" "571369" "516873" "566580" "477374"
## [22] "584457" "544636" "483005" "579305" "601496" "628320" "541907"
unique(qt4_5$Target)
## [1] "536346" "567195" "527449" "459381" "595298" "466907" "577992"
## [8] "537281" "523927" "595581" "642329" "503701" "571970" "644226"
## [15] "632961" "473173" "620120" "575030" "630626" "580426" "616315"
## [22] "520660" "589943" "569329" "588172" "492850" "636721" "580798"
## [29] "546593" "536906" "606730" "482012" "657526" "464579" "621924"
## [36] "503218" "557269" "640784" "655963" "639642" "585606" "571369"
## [43] "516873" "566580" "477374" "584457" "544636" "483005" "579305"
## [50] "601496" "628320" "541907"
unique(qt4_5$Weight)
## [1] 5352.39 1900.95 1574.64 1363.77 9000.70 1294.57 1895.87
## [8] 741.67 5666.86 1840.03 1267.62 7921.31 119.85 4204.22
## [15] 950.28 1737.76 6540.04 5627.55 5124.17 283.45 369.53
## [22] 1267.93 696.89 988.82 114.80 512.19 133.42 772.30
## [29] 447.06 2688.40 41.22 100.20 3734.96 2516.93 6672.05
## [36] 1243.11 500.25 1663.24 49.18 380.93 1598.86 355.75
## [43] 2215.63 392.32 344.50 512.35 15.21 1845.50 136.34
## [50] 734.04 311.58 1039.37 10152.60 498.36 450.54 630.62
## [57] 32.96 792.79 1878.82 115.42 1844.96 1525.27 173.56
## [64] 165.42 309.24 392.75 351.20 852.11 3283.68 278.73
## [71] 166.04 724.28 334.44 158.92 97.12 9245.31 4241.32
## [78] 667.15 1042.23 1011.45 679.18 4144.21 5961.09 1102.59
## [85] 1259.95 1277.66 1527.56 6321.04 2378.14 1986.66 9478.52
## [92] 18450.20 4410.78 19821.50 13157.70 8773.28 7720.52 37449.40
## [99] 2614.97 20352.50 115.79 4210.97 775.94 615.23 3991.31
## [106] 1168.89 2970.54 2.39 1021.95 720.96 609.94 1790.61
## [113] 2061.71 2165.12 1452.84 14649.50 426.21 109.02 48.73
## [120] 4.44 21.11 146.95 1975.82 168.32 17.58 262.83
## [127] 1334.54 187.42 1514.53 993.98 713.31 4659.92 1670.19
## [134] 509.54 187.26 198.14 594.06 209.50 413.23 18.64
## [141] 706.54 331.34 177.90 14.11 188.27 119.39 661.16
## [148] 224.71 486.33 1502.52 1639.51 646.98 240.67 569.33
## [155] 1862.42 400.82 2841.47 433.38 1235.58 252.20 1518.22
## [162] 149.78 44.14 983.64 796.16 864.13 432.71 3697.33
## [169] 6893.61 102.03 649.81 1237.39 377.67 6387.94 1444.46
## [176] 896.12 2708.62 984.37 691.57 2152.02 1133.34 417.98
## [183] 7935.60 317.61 655.13 730.33 422.10 49.47 203.94
## [190] 603.25 103.21 114.05 121.83 478.86 226.22 326.47
## [197] 1070.35 517.84 85.76 1351.44 4724.30 35.87 296.85
## [204] 23697.10 7517.28 905.62 1515.98 7064.27 3416.10 4569.15
## [211] 4425.31 5185.15 3230.10 1483.75 3670.14 524.95 1960.36
## [218] 2511.28 15948.00 15436.20 3952.68 2502.66 109907.00 854.36
## [225] 907.20 3262.45 355.30 782.44 692.16 553.99 419.38
## [232] 1965.25 277.86 1346.99 1379.15 2033.67 75.20 1415.71
## [239] 8.34 1451.89 1983.78 3458.50 450.07 850.33 17549.40
## [246] 636.46 1624.18 25.63 705.58 979.70 56.59 531.78
## [253] 317.77 611.41 1133.39 1002.26 67.06 395.03 61.78
## [260] 1396.83 426.85 6110.68 4660.12 563.88 3906.88 1746.28
## [267] 4328.33 580.13 1403.61 6710.84 2069.84 1752.47 4033.83
## [274] 6237.13 2505.02 13236.00 1469.80 5371.76 1665.05 2302.65
## [281] 25968.10 39565.60 4412.93 7855.50 141744.00 1118.65 1367.23
## [288] 364.94 875.90 2110.77 1033.21 4952.46 4771.52 552.41
## [295] 9585.05 3966.64 3586.36 3838.17 2835.05 3068.77 314.77
## [302] 1459.69 97608.40 10798.30 31264.80 67163.20 132.44 1740.54
## [309] 103.70 81.43 1583.24 49.59 1649.44 2275.25 1188.57
## [316] 221.39 584.72 106.88 3687.20 788.91 19.13 3158.36
## [323] 146.83 715.96 1045.51 272.05 330.65 692.91 56.24
## [330] 191.21 34.71 897.96 24.56 1136.23 180.66 2295.07
## [337] 64.76 622.83 710.23 1198.06 333.32 272.08 13703.40
## [344] 383.60 1488.77 1088.44 61.59 301.58 137.73 2064.53
## [351] 111.43 1285.34 53.76 31.71 843.95 1347.57 123.98
## [358] 594.22 127.35 736.57 2645.89 326.38 4963.30 648.85
## [365] 826.90 6870.03 11603.10 157.01 408.08 781.41 585.10
## [372] 1345.64 482.61 1823.33 266.98 3506.07 1135.68 1866.86
## [379] 78.41 31.31 362.15 7595.77 1166.13 777.87 38582.00
## [386] 304.09 309.77 562.84 743.14 273.13 424.78 1796.07
## [393] 265.53 2077.39 339.53 147.51 576.65 138.96 578.05
## [400] 856.97 839.07 950.07 269.26 1337.98 3561.76 4521.72
## [407] 415.16 1610.81 2358.23 709.81 902.26 5024.56 1704.00
## [414] 2187.16 181.37 2968.37 756.21 4096.56 3014.60 3210.12
## [421] 271.10 3653.69 301.26 80.93 874.84 17251.30 14454.60
## [428] 1119.39 27376.10 4789.41 483.42 430.54 466.44 813.91
## [435] 513.06 400.64 875.81 468.27 111.51 1547.32 391.11
## [442] 331.23 1009.57 168.60 1997.14 66.41 47.31 1078.45
## [449] 206.88 1817.39 8395.12 198.72 48.44 1444.23 414.14
## [456] 162.71 284.91 1626.88 235.40 597.67 151.93 940.97
## [463] 430.79 964.22 1019.65 669.50 2076.09 64.94 422.27
## [470] 208.23 335.43 356.86 1687.09 369.59 10065.50 2670.87
## [477] 1097.67 3.66 195.12 733.14 206.59 332.15 461.43
## [484] 245.00 371.91 465.34 492.28 120.76 435.81 114.54
## [491] 43.82 357.94 7219.68 7.79
qt4_5 <- subset(qt4_5, select = -c(SourceLocation, TargetLocation, SourceLatitude, SourceLongitude, TargetLatitude, TargetLongitude)) # SOurce and Target Latitude and Longitude columns removed as all Null.
colnames(qt4_5)
## [1] "Source" "eType" "Target" "Time" "Weight"
range(qt4_5$Source) # 466976 657076
## [1] "464579" "657526"
range(qt4_5$Target) # 459381 657076
## [1] "459381" "657526"
range(qt4_5$Time) # 31536000-31536000
## [1] 31536000 31536000
income_cat_qt4 <- NULL
# Income Categories:
for (i in (qt4_5$Source)) {
for (j in (cat$NodeID)) { # cat_list contains all the demographic nodeIDs (from the DemographicNodeExtraction Script)
if(i == j){
income_cat_qt4 <- append(income_cat_qt4,i)
}
}
}
print(income_cat_qt4) # income categories extracted
## [1] "510031" "510031" "510031" "510031" "510031" "510031" "510031"
## [8] "552988" "552988" "552988" "552988" "552988" "552988" "552988"
## [15] "552988" "552988" "552988" "620120" "620120" "552988" "620120"
## [22] "510031" "552988" "510031" "552988" "510031" "552988" "510031"
## [29] "552988" "552988" "510031" "552988" "552988" "510031" "552988"
## [36] "510031" "552988" "552988" "620120" "510031" "552988" "552988"
## [43] "510031" "552988" "510031" "552988" "620120"
unique(income_cat_qt4) # 3
## [1] "510031" "552988" "620120"
qt4_5_sub1 <- subset(qt4_5, qt4_5$Source == income_cat_qt4) # Subset of data with only income categories
## Warning in qt4_5$Source == income_cat_qt4: longer object length is not a
## multiple of shorter object length
str(qt4_5_sub1)
## 'data.frame': 16 obs. of 5 variables:
## $ Source: chr "510031" "552988" "552988" "552988" ...
## $ eType : int 5 5 5 5 5 5 5 5 5 5 ...
## $ Target: chr "569329" "569329" "588172" "557269" ...
## $ Time : int 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 ...
## $ Weight: num 498 9479 4411 4724 2503 ...
plot(qt4_5_sub1$Source, qt4_5_sub1$Weight) # Plot of Monetary income in each category
# Expense Categories:
expense_cat_qt4 <- NULL
for (k in qt4_5$Target) {
for(l in cat$NodeID){
if(k==l){
expense_cat_qt4 <- append(expense_cat_qt4, k)
}
}
}
print(expense_cat_qt4) # expense categories extracted
## [1] "536346" "567195" "527449" "459381" "595298" "466907" "577992"
## [8] "537281" "523927" "595581" "642329" "503701" "571970" "644226"
## [15] "632961" "473173" "620120" "575030" "630626" "527449" "459381"
## [22] "595298" "466907" "577992" "537281" "580426" "595581" "616315"
## [29] "642329" "503701" "571970" "632961" "473173" "620120" "575030"
## [36] "536346" "520660" "567195" "527449" "459381" "595298" "466907"
## [43] "589943" "537281" "523927" "580426" "595581" "503701" "571970"
## [50] "644226" "473173" "620120" "575030" "630626" "567195" "527449"
## [57] "459381" "595298" "466907" "606730" "589943" "577992" "537281"
## [64] "616315" "642329" "632961" "473173" "620120" "630626" "567195"
## [71] "527449" "459381" "595298" "466907" "589943" "577992" "537281"
## [78] "580426" "595581" "642329" "503701" "473173" "620120" "536346"
## [85] "567195" "527449" "459381" "595298" "466907" "577992" "523927"
## [92] "580426" "595581" "616315" "503701" "644226" "473173" "620120"
## [99] "575030" "536346" "567195" "527449" "459381" "595298" "466907"
## [106] "577992" "537281" "523927" "580426" "616315" "642329" "503701"
## [113] "644226" "473173" "575030" "630626" "567195" "527449" "459381"
## [120] "595298" "466907" "577992" "537281" "523927" "616315" "642329"
## [127] "571970" "632961" "473173" "620120" "621924" "630626" "567195"
## [134] "527449" "459381" "595298" "466907" "589943" "595581" "616315"
## [141] "642329" "503701" "571970" "632961" "473173" "621924" "503218"
## [148] "536346" "520660" "567195" "527449" "459381" "595298" "466907"
## [155] "589943" "577992" "537281" "580426" "595581" "616315" "503701"
## [162] "644226" "473173" "620120" "621924" "536346" "520660" "567195"
## [169] "527449" "459381" "595298" "466907" "606730" "537281" "523927"
## [176] "580426" "595581" "503701" "644226" "473173" "621924" "640784"
## [183] "630626" "567195" "527449" "459381" "595298" "466907" "589943"
## [190] "577992" "523927" "580426" "616315" "642329" "571970" "632961"
## [197] "473173" "620120" "575030" "621924" "536346" "520660" "567195"
## [204] "527449" "459381" "595298" "466907" "577992" "523927" "580426"
## [211] "595581" "642329" "503701" "571970" "644226" "632961" "473173"
## [218] "620120" "575030" "621924" "503218" "536346" "527449" "459381"
## [225] "595298" "466907" "589943" "537281" "595581" "616315" "503701"
## [232] "571970" "644226" "632961" "473173" "620120" "575030" "621924"
## [239] "640784" "536346" "527449" "459381" "595298" "466907" "577992"
## [246] "595581" "616315" "642329" "503701" "571970" "644226" "632961"
## [253] "473173" "620120" "575030" "621924" "640784" "536346" "527449"
## [260] "459381" "595298" "466907" "589943" "577992" "537281" "523927"
## [267] "580426" "616315" "642329" "503701" "644226" "632961" "473173"
## [274] "620120" "575030" "621924" "640784" "630626" "527449" "459381"
## [281] "595298" "466907" "577992" "523927" "616315" "632961" "473173"
## [288] "620120" "575030" "621924" "640784" "536346" "567195" "527449"
## [295] "459381" "595298" "466907" "589943" "537281" "523927" "580426"
## [302] "595581" "642329" "503701" "571970" "644226" "473173" "620120"
## [309] "575030" "621924" "640784" "536346" "567195" "527449" "459381"
## [316] "595298" "589943" "537281" "523927" "580426" "595581" "616315"
## [323] "503701" "571970" "644226" "473173" "620120" "575030" "640784"
## [330] "503218" "630626" "567195" "527449" "459381" "595298" "466907"
## [337] "577992" "537281" "523927" "580426" "595581" "616315" "503701"
## [344] "571970" "632961" "473173" "620120" "575030" "640784" "503218"
## [351] "536346" "567195" "527449" "459381" "595298" "466907" "577992"
## [358] "537281" "523927" "580426" "595581" "616315" "642329" "503701"
## [365] "644226" "473173" "575030" "621924" "536346" "567195" "527449"
## [372] "459381" "595298" "466907" "589943" "537281" "523927" "580426"
## [379] "595581" "616315" "642329" "571970" "644226" "632961" "473173"
## [386] "620120" "575030" "621924" "630626" "567195" "527449" "459381"
## [393] "595298" "466907" "606730" "589943" "577992" "537281" "523927"
## [400] "580426" "595581" "616315" "642329" "503701" "571970" "632961"
## [407] "473173" "620120" "575030" "640784" "536346" "520660" "567195"
## [414] "527449" "459381" "595298" "466907" "577992" "537281" "523927"
## [421] "580426" "595581" "616315" "642329" "503701" "571970" "644226"
## [428] "632961" "473173" "620120" "575030" "630626" "567195" "527449"
## [435] "459381" "595298" "466907" "606730" "589943" "537281" "580426"
## [442] "595581" "616315" "642329" "503701" "632961" "473173"
unique(expense_cat_qt4) # 27
## [1] "536346" "567195" "527449" "459381" "595298" "466907" "577992"
## [8] "537281" "523927" "595581" "642329" "503701" "571970" "644226"
## [15] "632961" "473173" "620120" "575030" "630626" "580426" "616315"
## [22] "520660" "589943" "606730" "621924" "503218" "640784"
qt4_5_sub2 <- subset(qt4_5, qt4_5$Target == expense_cat_qt4) # Subset of data with only expense categories
## Warning in qt4_5$Target == expense_cat_qt4: longer object length is not a
## multiple of shorter object length
str(qt4_5_sub2)
## 'data.frame': 66 obs. of 5 variables:
## $ Source: chr "464579" "464579" "464579" "464579" ...
## $ eType : int 5 5 5 5 5 5 5 5 5 5 ...
## $ Target: chr "536346" "567195" "527449" "459381" ...
## $ Time : int 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 ...
## $ Weight: num 5352 1901 1575 1364 9001 ...
plot(qt4_5_sub2$Target, qt4_5_sub2$Weight) # Plot of Monetary expenses in each category
hist(qt4_5$Weight)
unique(qt4_5$Weight)
## [1] 5352.39 1900.95 1574.64 1363.77 9000.70 1294.57 1895.87
## [8] 741.67 5666.86 1840.03 1267.62 7921.31 119.85 4204.22
## [15] 950.28 1737.76 6540.04 5627.55 5124.17 283.45 369.53
## [22] 1267.93 696.89 988.82 114.80 512.19 133.42 772.30
## [29] 447.06 2688.40 41.22 100.20 3734.96 2516.93 6672.05
## [36] 1243.11 500.25 1663.24 49.18 380.93 1598.86 355.75
## [43] 2215.63 392.32 344.50 512.35 15.21 1845.50 136.34
## [50] 734.04 311.58 1039.37 10152.60 498.36 450.54 630.62
## [57] 32.96 792.79 1878.82 115.42 1844.96 1525.27 173.56
## [64] 165.42 309.24 392.75 351.20 852.11 3283.68 278.73
## [71] 166.04 724.28 334.44 158.92 97.12 9245.31 4241.32
## [78] 667.15 1042.23 1011.45 679.18 4144.21 5961.09 1102.59
## [85] 1259.95 1277.66 1527.56 6321.04 2378.14 1986.66 9478.52
## [92] 18450.20 4410.78 19821.50 13157.70 8773.28 7720.52 37449.40
## [99] 2614.97 20352.50 115.79 4210.97 775.94 615.23 3991.31
## [106] 1168.89 2970.54 2.39 1021.95 720.96 609.94 1790.61
## [113] 2061.71 2165.12 1452.84 14649.50 426.21 109.02 48.73
## [120] 4.44 21.11 146.95 1975.82 168.32 17.58 262.83
## [127] 1334.54 187.42 1514.53 993.98 713.31 4659.92 1670.19
## [134] 509.54 187.26 198.14 594.06 209.50 413.23 18.64
## [141] 706.54 331.34 177.90 14.11 188.27 119.39 661.16
## [148] 224.71 486.33 1502.52 1639.51 646.98 240.67 569.33
## [155] 1862.42 400.82 2841.47 433.38 1235.58 252.20 1518.22
## [162] 149.78 44.14 983.64 796.16 864.13 432.71 3697.33
## [169] 6893.61 102.03 649.81 1237.39 377.67 6387.94 1444.46
## [176] 896.12 2708.62 984.37 691.57 2152.02 1133.34 417.98
## [183] 7935.60 317.61 655.13 730.33 422.10 49.47 203.94
## [190] 603.25 103.21 114.05 121.83 478.86 226.22 326.47
## [197] 1070.35 517.84 85.76 1351.44 4724.30 35.87 296.85
## [204] 23697.10 7517.28 905.62 1515.98 7064.27 3416.10 4569.15
## [211] 4425.31 5185.15 3230.10 1483.75 3670.14 524.95 1960.36
## [218] 2511.28 15948.00 15436.20 3952.68 2502.66 109907.00 854.36
## [225] 907.20 3262.45 355.30 782.44 692.16 553.99 419.38
## [232] 1965.25 277.86 1346.99 1379.15 2033.67 75.20 1415.71
## [239] 8.34 1451.89 1983.78 3458.50 450.07 850.33 17549.40
## [246] 636.46 1624.18 25.63 705.58 979.70 56.59 531.78
## [253] 317.77 611.41 1133.39 1002.26 67.06 395.03 61.78
## [260] 1396.83 426.85 6110.68 4660.12 563.88 3906.88 1746.28
## [267] 4328.33 580.13 1403.61 6710.84 2069.84 1752.47 4033.83
## [274] 6237.13 2505.02 13236.00 1469.80 5371.76 1665.05 2302.65
## [281] 25968.10 39565.60 4412.93 7855.50 141744.00 1118.65 1367.23
## [288] 364.94 875.90 2110.77 1033.21 4952.46 4771.52 552.41
## [295] 9585.05 3966.64 3586.36 3838.17 2835.05 3068.77 314.77
## [302] 1459.69 97608.40 10798.30 31264.80 67163.20 132.44 1740.54
## [309] 103.70 81.43 1583.24 49.59 1649.44 2275.25 1188.57
## [316] 221.39 584.72 106.88 3687.20 788.91 19.13 3158.36
## [323] 146.83 715.96 1045.51 272.05 330.65 692.91 56.24
## [330] 191.21 34.71 897.96 24.56 1136.23 180.66 2295.07
## [337] 64.76 622.83 710.23 1198.06 333.32 272.08 13703.40
## [344] 383.60 1488.77 1088.44 61.59 301.58 137.73 2064.53
## [351] 111.43 1285.34 53.76 31.71 843.95 1347.57 123.98
## [358] 594.22 127.35 736.57 2645.89 326.38 4963.30 648.85
## [365] 826.90 6870.03 11603.10 157.01 408.08 781.41 585.10
## [372] 1345.64 482.61 1823.33 266.98 3506.07 1135.68 1866.86
## [379] 78.41 31.31 362.15 7595.77 1166.13 777.87 38582.00
## [386] 304.09 309.77 562.84 743.14 273.13 424.78 1796.07
## [393] 265.53 2077.39 339.53 147.51 576.65 138.96 578.05
## [400] 856.97 839.07 950.07 269.26 1337.98 3561.76 4521.72
## [407] 415.16 1610.81 2358.23 709.81 902.26 5024.56 1704.00
## [414] 2187.16 181.37 2968.37 756.21 4096.56 3014.60 3210.12
## [421] 271.10 3653.69 301.26 80.93 874.84 17251.30 14454.60
## [428] 1119.39 27376.10 4789.41 483.42 430.54 466.44 813.91
## [435] 513.06 400.64 875.81 468.27 111.51 1547.32 391.11
## [442] 331.23 1009.57 168.60 1997.14 66.41 47.31 1078.45
## [449] 206.88 1817.39 8395.12 198.72 48.44 1444.23 414.14
## [456] 162.71 284.91 1626.88 235.40 597.67 151.93 940.97
## [463] 430.79 964.22 1019.65 669.50 2076.09 64.94 422.27
## [470] 208.23 335.43 356.86 1687.09 369.59 10065.50 2670.87
## [477] 1097.67 3.66 195.12 733.14 206.59 332.15 461.43
## [484] 245.00 371.91 465.34 492.28 120.76 435.81 114.54
## [491] 43.82 357.94 7219.68 7.79
range(qt4_5$Weight) #2.39 141744.00
## [1] 2.39 141744.00
# To-do : normalise the weights to better visualise in graph. Convert to csv maybe.
Graph 5 Analysis:
# Load The Data:
qt5 <- data.table::fread(here::here("data", "Q1-Graph5.csv"))
head(qt5)
## Source eType Target Time Weight SourceLocation TargetLocation
## 1: 619322 3 590442 96346 17 NA NA
## 2: 594308 0 549840 105656 1 NA NA
## 3: 524153 3 629769 307922 4 NA NA
## 4: 524153 3 461577 449990 1923 NA NA
## 5: 619322 3 547205 634562 242 NA NA
## 6: 483784 0 631903 975525 1 NA NA
## SourceLatitude SourceLongitude TargetLatitude TargetLongitude
## 1: NA NA NA NA
## 2: NA NA NA NA
## 3: NA NA NA NA
## 4: NA NA NA NA
## 5: NA NA NA NA
## 6: NA NA NA NA
tail(qt5)
## Source eType Target Time Weight SourceLocation TargetLocation
## 1: 573137 5 632961 31536000 297.91 NA NA
## 2: 573137 5 473173 31536000 248.56 NA NA
## 3: 573137 5 620120 31536000 1295.19 NA NA
## 4: 573137 5 575030 31536000 4835.03 NA NA
## 5: 573137 5 621924 31536000 328.93 NA NA
## 6: 552988 5 573137 31536000 11488.30 NA NA
## SourceLatitude SourceLongitude TargetLatitude TargetLongitude
## 1: NA NA NA NA
## 2: NA NA NA NA
## 3: NA NA NA NA
## 4: NA NA NA NA
## 5: NA NA NA NA
## 6: NA NA NA NA
# Summarising the Data:
summary(qt5)
## Source eType Target Time
## Min. :477657 Min. :0.000 Min. :459381 Min. : 96346
## 1st Qu.:510031 1st Qu.:5.000 1st Qu.:523927 1st Qu.:14947200
## Median :552988 Median :5.000 Median :567195 Median :31536000
## Mean :553140 Mean :4.635 Mean :566074 Mean :23453574
## 3rd Qu.:594308 3rd Qu.:6.000 3rd Qu.:616453 3rd Qu.:31536000
## Max. :631903 Max. :6.000 Max. :657173 Max. :31536000
##
## Weight SourceLocation TargetLocation SourceLatitude
## Min. : -1.0 Min. :0.000 Min. :0.000 Min. :-29.000
## 1st Qu.: 1.0 1st Qu.:2.000 1st Qu.:1.000 1st Qu.:-25.000
## Median : 198.0 Median :2.500 Median :3.000 Median :-22.000
## Mean : 2758.5 Mean :2.355 Mean :2.718 Mean : -6.987
## 3rd Qu.: 983.4 3rd Qu.:3.000 3rd Qu.:5.000 3rd Qu.: 1.000
## Max. :441206.0 Max. :5.000 Max. :5.000 Max. : 33.000
## NA's :271 NA's :271 NA's :271
## SourceLongitude TargetLatitude TargetLongitude
## Min. :-170.65 Min. :-29.000 Min. :-170.65
## 1st Qu.:-111.00 1st Qu.:-22.000 1st Qu.:-111.00
## Median : -41.00 Median : 22.000 Median : -41.00
## Mean : -37.91 Mean : 6.702 Mean : -13.75
## 3rd Qu.: 91.00 3rd Qu.: 23.281 3rd Qu.: 152.20
## Max. : 156.00 Max. : 33.000 Max. : 156.00
## NA's :271 NA's :271 NA's :271
nrow(qt5) #395
## [1] 395
ncol(qt5) #11
## [1] 11
qt5$Source <- as.character(qt5$Source)
qt5$Target <- as.character(qt5$Target)
# Differentiating between channels:
qt5_01 <- qt5 %>% filter(qt5$eType == 0 | qt5$eType == 1) # Communication Channel
nrow(qt5_01) # 31
## [1] 31
qt5_23 <- qt5 %>% filter(qt5$eType == 2 | qt5$eType == 3) # Procurement Channel
nrow(qt5_23) # 51
## [1] 51
qt5_4 <- qt5 %>% filter(qt5$eType == 4) # Co-authorship Channel
nrow(qt5_4) # 0
## [1] 0
qt5_5 <- qt5 %>% filter(qt5$eType == 5) # Demographic Channel
nrow(qt5_5) # 203
## [1] 203
qt5_6 <- qt5 %>% filter(qt5$eType == 6) # Travel Channel
nrow(qt5_6) # 110
## [1] 110
# Highest data for Demographic, Travel Channel and Procurement.
# Analysis of the Communication channel:
glimpse(qt5_01)
## Observations: 31
## Variables: 11
## $ Source <chr> "594308", "483784", "549840", "594308", "48378...
## $ eType <int> 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0...
## $ Target <chr> "549840", "631903", "619322", "477657", "61932...
## $ Time <int> 105656, 975525, 1674004, 2053209, 4699152, 792...
## $ Weight <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1...
## $ SourceLocation <int> NA, NA, NA, 2, 0, 0, 4, 3, 2, 0, NA, NA, 4, NA...
## $ TargetLocation <int> NA, NA, NA, 4, 3, 1, 1, 3, 5, 5, NA, NA, 3, NA...
## $ SourceLatitude <dbl> NA, NA, NA, -24.176100, 32.250300, 32.250300, ...
## $ SourceLongitude <dbl> NA, NA, NA, 93.8902, -40.4067, -40.4067, -170....
## $ TargetLatitude <dbl> NA, NA, NA, -1.17279, -24.22860, -27.47660, -2...
## $ TargetLongitude <dbl> NA, NA, NA, -170.6460, -111.1290, -14.6148, -1...
#unique(qt5_01)
unique(qt5_01$eType) # 0 1
## [1] 0 1
unique(qt5_01$SourceLocation) # NA 2 0 4 3
## [1] NA 2 0 4 3
unique(qt5_01$TargetLocation) # NA 4 3 1 5
## [1] NA 4 3 1 5
unique(qt5_01$SourceLatitude)
## [1] NA -24.176100 32.250300 -1.172790 -24.228600 0.259451
## [7] -25.031300
unique(qt5_01$SourceLongitude)
## [1] NA 93.8902 -40.4067 -170.6460 -111.1290 -165.5760 -110.7380
unique(qt5_01$TargetLatitude)
## [1] NA -1.17279 -24.22860 -27.47660 -25.03130 25.55350 22.52320
unique(qt5_01$TargetLongitude)
## [1] NA -170.6460 -111.1290 -14.6148 -110.7380 153.2350 151.8550
unique(qt5_01$Source)
## [1] "594308" "483784" "549840" "477657" "619322" "524153" "573137"
## [8] "530990" "631903" "561819"
unique(qt5_01$Target)
## [1] "549840" "631903" "619322" "477657" "561819" "530990" "594308" "524153"
## [9] "573137"
colnames(qt5_01)
## [1] "Source" "eType" "Target"
## [4] "Time" "Weight" "SourceLocation"
## [7] "TargetLocation" "SourceLatitude" "SourceLongitude"
## [10] "TargetLatitude" "TargetLongitude"
# Analysis of the Demographic channel:
glimpse(qt5_5)
## Observations: 203
## Variables: 11
## $ Source <chr> "483784", "483784", "483784", "483784", "48378...
## $ eType <int> 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5...
## $ Target <chr> "503218", "536346", "520660", "567195", "52744...
## $ Time <int> 31536000, 31536000, 31536000, 31536000, 315360...
## $ Weight <dbl> 5148.59, 12802.80, 31733.80, 29938.60, 983.85,...
## $ SourceLocation <int> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLocation <int> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ SourceLatitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ SourceLongitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLatitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ TargetLongitude <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
#unique(qt5_5)
unique(qt5_5$eType) # 5
## [1] 5
unique(qt5_5$SourceLocation) # NA
## [1] NA
unique(qt5_5$TargetLocation) # NA
## [1] NA
unique(qt5_5$SourceLatitude) # NA
## [1] NA
unique(qt5_5$SourceLongitude) # NA
## [1] NA
unique(qt5_5$TargetLatitude) # NA
## [1] NA
unique(qt5_5$TargetLongitude) # NA
## [1] NA
unique(qt5_5$Source)
## [1] "483784" "510031" "552988" "620120" "561819" "530990" "619322"
## [8] "631903" "524153" "549840" "477657" "594308" "573137"
unique(qt5_5$Target)
## [1] "503218" "536346" "520660" "567195" "527449" "459381" "595298"
## [8] "466907" "589943" "577992" "537281" "523927" "580426" "595581"
## [15] "616315" "642329" "503701" "571970" "644226" "632961" "473173"
## [22] "483784" "620120" "575030" "621924" "561819" "640784" "530990"
## [29] "619322" "630626" "606730" "631903" "524153" "549840" "477657"
## [36] "594308" "573137"
unique(qt5_5$Weight)
## [1] 5148.59 12802.80 31733.80 29938.60 983.85 1728.16 6120.39
## [8] 2657.09 10303.10 18663.50 1956.93 5330.29 18354.90 8666.52
## [15] 36827.80 8277.90 17303.80 1340.05 7333.98 2588.25 572.69
## [22] 1201.05 441206.00 2356.79 729.34 1268.58 109.98 61.95
## [29] 699.05 303.21 541.51 366.28 1011.27 922.76 982.87
## [36] 418.66 421.73 661.68 1027.12 262.73 2435.24 460.37
## [43] 2497.95 417.69 11074.40 130.95 1109.22 3451.82 267.97
## [50] 216.43 2126.40 29.42 2583.05 390.48 749.67 612.18
## [57] 797.33 2692.27 134.41 62.83 590.84 3139.99 7510.12
## [64] 325.81 21534.10 444.76 1982.88 4452.55 62.80 379.61
## [71] 1133.88 655.16 83.88 235.34 534.96 521.92 1411.22
## [78] 1183.04 253.08 112.12 302.50 248.96 1504.41 5634.90
## [85] 712.17 25157.90 310.16 3654.46 236.72 205.47 1661.68
## [92] 794.81 268.99 1605.74 717.54 2819.24 529.93 355.59
## [99] 2988.87 62.49 822.66 3515.59 5123.35 23118.10 229.28
## [106] 3631.34 1348.59 1171.36 7740.68 143.57 4739.40 315.31
## [113] 507.95 3609.81 930.86 6028.10 11.03 2189.28 21.71
## [120] 1807.45 17503.10 3196.25 4561.47 23069.80 205.38 713.73
## [127] 2024.76 223.53 574.87 195.71 386.66 1291.33 2987.84
## [134] 392.46 345.49 216.70 2683.20 643.26 273.58 1676.57
## [141] 653.86 4156.52 248.04 762.06 10144.00 101.86 1164.18
## [148] 118.60 116.35 146.31 718.46 252.01 565.75 302.61
## [155] 581.82 513.34 0.17 437.04 162.53 2123.92 392.38
## [162] 3562.94 2416.01 2240.53 3651.56 487.49 298.61 81.19
## [169] 632.36 71.01 2959.18 247.67 3002.98 2958.78 571.12
## [176] 1019.14 974.96 284.64 657.17 3468.46 6971.99 190.00
## [183] 1693.86 33720.80 581.83 254.74 1357.29 45.68 210.35
## [190] 1725.25 322.40 2555.90 83.46 426.33 53.93 625.06
## [197] 1210.40 297.91 248.56 1295.19 4835.03 328.93 11488.30
qt5_5 <- subset(qt5_5, select = -c(SourceLocation, TargetLocation, SourceLatitude, SourceLongitude, TargetLatitude, TargetLongitude)) # SOurce and Target Latitude and Longitude columns removed as all Null.
colnames(qt5_5)
## [1] "Source" "eType" "Target" "Time" "Weight"
range(qt5_5$Source) # 466976 657076
## [1] "477657" "631903"
range(qt5_5$Target) # 459381 657076
## [1] "459381" "644226"
range(qt5_5$Time) # 31536000-31536000
## [1] 31536000 31536000
income_cat_qt5 <- NULL
# Income Categories:
for (i in (qt5_5$Source)) {
for (j in (cat$NodeID)) { # cat_list contains all the demographic nodeIDs (from the DemographicNodeExtraction Script)
if(i == j){
income_cat_qt5 <- append(income_cat_qt5,i)
}
}
}
print(income_cat_qt5) # income categories extracted
## [1] "510031" "552988" "620120" "552988" "510031" "552988" "552988"
## [8] "552988" "510031" "552988" "510031" "552988" "510031" "552988"
## [15] "510031" "552988" "552988"
unique(income_cat_qt5) # 3
## [1] "510031" "552988" "620120"
qt5_5_sub1 <- subset(qt5_5, qt5_5$Source == income_cat_qt5) # Subset of data with only income categories
## Warning in qt5_5$Source == income_cat_qt5: longer object length is not a
## multiple of shorter object length
str(qt5_5_sub1)
## 'data.frame': 8 obs. of 5 variables:
## $ Source: chr "510031" "552988" "510031" "552988" ...
## $ eType : int 5 5 5 5 5 5 5 5
## $ Target: chr "483784" "483784" "530990" "530990" ...
## $ Time : int 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000
## $ Weight: num 1201 441206 326 21534 23118 ...
plot(qt5_5_sub1$Source, qt5_5_sub1$Weight) # Plot of Monetary income in each category
# Expense Categories:
expense_cat_qt5 <- NULL
for (k in qt5_5$Target) {
for(l in cat$NodeID){
if(k==l){
expense_cat_qt5 <- append(expense_cat_qt5, k)
}
}
}
print(expense_cat_qt5) # expense categories extracted
## [1] "503218" "536346" "520660" "567195" "527449" "459381" "595298"
## [8] "466907" "589943" "577992" "537281" "523927" "580426" "595581"
## [15] "616315" "642329" "503701" "571970" "644226" "632961" "473173"
## [22] "536346" "567195" "527449" "459381" "595298" "466907" "589943"
## [29] "577992" "537281" "523927" "595581" "616315" "642329" "503701"
## [36] "644226" "632961" "473173" "620120" "575030" "621924" "640784"
## [43] "536346" "567195" "527449" "459381" "595298" "466907" "589943"
## [50] "537281" "580426" "595581" "616315" "503701" "644226" "632961"
## [57] "473173" "620120" "575030" "640784" "536346" "567195" "527449"
## [64] "459381" "595298" "466907" "577992" "537281" "580426" "595581"
## [71] "616315" "642329" "503701" "571970" "644226" "632961" "473173"
## [78] "620120" "621924" "640784" "630626" "527449" "459381" "595298"
## [85] "466907" "606730" "589943" "537281" "523927" "580426" "595581"
## [92] "503701" "571970" "473173" "620120" "575030" "640784" "536346"
## [99] "527449" "459381" "595298" "466907" "589943" "537281" "595581"
## [106] "616315" "642329" "503701" "571970" "644226" "473173" "620120"
## [113] "575030" "621924" "640784" "536346" "567195" "527449" "459381"
## [120] "595298" "466907" "589943" "577992" "537281" "523927" "616315"
## [127] "503701" "644226" "632961" "473173" "620120" "575030" "621924"
## [134] "640784" "630626" "567195" "527449" "459381" "595298" "466907"
## [141] "589943" "595581" "616315" "503701" "571970" "473173" "620120"
## [148] "575030" "536346" "520660" "567195" "527449" "459381" "595298"
## [155] "466907" "589943" "523927" "580426" "595581" "616315" "642329"
## [162] "503701" "644226" "632961" "473173" "620120" "575030" "621924"
## [169] "640784" "630626" "567195" "527449" "459381" "595298" "466907"
## [176] "589943" "577992" "537281" "580426" "595581" "503701" "632961"
## [183] "473173" "620120" "575030" "621924"
unique(expense_cat_qt5) # 27
## [1] "503218" "536346" "520660" "567195" "527449" "459381" "595298"
## [8] "466907" "589943" "577992" "537281" "523927" "580426" "595581"
## [15] "616315" "642329" "503701" "571970" "644226" "632961" "473173"
## [22] "620120" "575030" "621924" "640784" "630626" "606730"
qt5_5_sub2 <- subset(qt5_5, qt5_5$Target == expense_cat_qt5) # Subset of data with only expense categories
## Warning in qt5_5$Target == expense_cat_qt5: longer object length is not a
## multiple of shorter object length
str(qt5_5_sub2)
## 'data.frame': 21 obs. of 5 variables:
## $ Source: chr "483784" "483784" "483784" "483784" ...
## $ eType : int 5 5 5 5 5 5 5 5 5 5 ...
## $ Target: chr "503218" "536346" "520660" "567195" ...
## $ Time : int 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 31536000 ...
## $ Weight: num 5149 12803 31734 29939 984 ...
plot(qt5_5_sub2$Target, qt5_5_sub2$Weight) # Plot of Monetary expenses in each category
hist(qt5_5$Weight)
unique(qt5_5$Weight)
## [1] 5148.59 12802.80 31733.80 29938.60 983.85 1728.16 6120.39
## [8] 2657.09 10303.10 18663.50 1956.93 5330.29 18354.90 8666.52
## [15] 36827.80 8277.90 17303.80 1340.05 7333.98 2588.25 572.69
## [22] 1201.05 441206.00 2356.79 729.34 1268.58 109.98 61.95
## [29] 699.05 303.21 541.51 366.28 1011.27 922.76 982.87
## [36] 418.66 421.73 661.68 1027.12 262.73 2435.24 460.37
## [43] 2497.95 417.69 11074.40 130.95 1109.22 3451.82 267.97
## [50] 216.43 2126.40 29.42 2583.05 390.48 749.67 612.18
## [57] 797.33 2692.27 134.41 62.83 590.84 3139.99 7510.12
## [64] 325.81 21534.10 444.76 1982.88 4452.55 62.80 379.61
## [71] 1133.88 655.16 83.88 235.34 534.96 521.92 1411.22
## [78] 1183.04 253.08 112.12 302.50 248.96 1504.41 5634.90
## [85] 712.17 25157.90 310.16 3654.46 236.72 205.47 1661.68
## [92] 794.81 268.99 1605.74 717.54 2819.24 529.93 355.59
## [99] 2988.87 62.49 822.66 3515.59 5123.35 23118.10 229.28
## [106] 3631.34 1348.59 1171.36 7740.68 143.57 4739.40 315.31
## [113] 507.95 3609.81 930.86 6028.10 11.03 2189.28 21.71
## [120] 1807.45 17503.10 3196.25 4561.47 23069.80 205.38 713.73
## [127] 2024.76 223.53 574.87 195.71 386.66 1291.33 2987.84
## [134] 392.46 345.49 216.70 2683.20 643.26 273.58 1676.57
## [141] 653.86 4156.52 248.04 762.06 10144.00 101.86 1164.18
## [148] 118.60 116.35 146.31 718.46 252.01 565.75 302.61
## [155] 581.82 513.34 0.17 437.04 162.53 2123.92 392.38
## [162] 3562.94 2416.01 2240.53 3651.56 487.49 298.61 81.19
## [169] 632.36 71.01 2959.18 247.67 3002.98 2958.78 571.12
## [176] 1019.14 974.96 284.64 657.17 3468.46 6971.99 190.00
## [183] 1693.86 33720.80 581.83 254.74 1357.29 45.68 210.35
## [190] 1725.25 322.40 2555.90 83.46 426.33 53.93 625.06
## [197] 1210.40 297.91 248.56 1295.19 4835.03 328.93 11488.30
range(qt5_5$Weight) #0.17 441206.00
## [1] 0.17 441206.00
# To-do : normalise the weights to better visualise in graph. Convert to csv maybe.
Parallel Coordinates for Template and Graph Data:
colnames(dt)
## [1] "Source" "eType" "Target"
## [4] "Time" "Weight" "SourceLocation"
## [7] "TargetLocation" "SourceLatitude" "SourceLongitude"
## [10] "TargetLatitude" "TargetLongitude"
ggparcoord(dt, columns = c(1,3,4,5), groupColumn = 4) # Parallel Coords for the Template
ggparcoord(qt1, columns = c(1,3,4,5), groupColumn = 4) # Parallel Coords for Graph 1
ggparcoord(qt2, columns = c(1,3,4,5), groupColumn = 4) # Parallel Coords for Graph 2
ggparcoord(qt3, columns = c(1,3,4,5), groupColumn = 4) # Parallel Coords for Graph 3
ggparcoord(qt4, columns = c(1,3,4,5), groupColumn = 4) # Parallel Coords for Graph 4
ggparcoord(qt5, columns = c(1,3,4,5), groupColumn = 4) # Parallel Coords for Graph 5
Communication Channel:
com_temp <- ggparcoord(dt01,columns = c(1,3,4,5), groupColumn = 4)
com_g1<- ggparcoord(qt1_01,columns = c(1,3,4,5), groupColumn = 4)
com_g2 <- ggparcoord(qt2_01,columns = c(1,3,4,5), groupColumn = 4)
com_g3 <- ggparcoord(qt3_01,columns = c(1,3,4,5), groupColumn = 4)
com_g4 <- ggparcoord(qt4_01,columns = c(1,3,4,5), groupColumn = 4)
com_g5 <- ggparcoord(qt5_01,columns = c(1,3,4,5), groupColumn = 4)
ggarrange(com_temp, com_g1, labels = c("Template", "Graph 1"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(com_temp, com_g2, labels = c("Template", "Graph 2"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(com_temp, com_g3, labels = c("Template", "Graph 3"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(com_temp, com_g4, labels = c("Template", "Graph 4"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(com_temp, com_g5, labels = c("Template", "Graph 5"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
Demographic Channel:
dem_temp <- ggparcoord(dt5, columns = c(1,3,4,5),groupColumn = 4)
dem_g1<- ggparcoord(qt1_5,columns = c(1,3,4,5), groupColumn = 4)
dem_g2 <- ggparcoord(qt2_5,columns = c(1,3,4,5), groupColumn = 4)
dem_g3 <- ggparcoord(qt3_5,columns = c(1,3,4,5), groupColumn = 4)
dem_g4 <- ggparcoord(qt4_5,columns = c(1,3,4,5), groupColumn = 4)
dem_g5 <- ggparcoord(qt5_5,columns = c(1,3,4,5), groupColumn = 4)
ggarrange(dem_temp, dem_g1, labels = c("Template", "Graph 1"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(dem_temp, dem_g2, labels = c("Template", "Graph 2"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(dem_temp, dem_g3, labels = c("Template", "Graph 3"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(dem_temp, dem_g4, labels = c("Template", "Graph 4"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(dem_temp, dem_g5, labels = c("Template", "Graph 5"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
Travel Channel:
tra_temp <- ggparcoord(dt6, columns = c(1,3,4,5),groupColumn = 4)
tra_g1<- ggparcoord(qt1_6,columns = c(1,3,4,5),groupColumn = 4)
tra_g2<- ggparcoord(qt2_6,columns = c(1,3,4,5),groupColumn = 4)
tra_g3<- ggparcoord(qt3_6,columns = c(1,3,4,5),groupColumn = 4)
tra_g4<- ggparcoord(qt4_6,columns = c(1,3,4,5),groupColumn = 4)
tra_g5<- ggparcoord(qt5_6,columns = c(1,3,4,5),groupColumn = 4)
ggarrange(tra_temp, tra_g1, labels = c("Template", "Graph 1"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(tra_temp, tra_g2, labels = c("Template", "Graph 2"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(tra_temp, tra_g3, labels = c("Template", "Graph 3"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(tra_temp, tra_g4, labels = c("Template", "Graph 4"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(tra_temp, tra_g5, labels = c("Template", "Graph 5"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
Procurement Channel:
pro_temp <- ggparcoord(dt23, columns = c(1,3,4,5),groupColumn = 4,scale = "center")
pro_g1<- ggparcoord(qt1_23,columns = c(1,3,4,5), groupColumn = 4, scale = "center")
pro_g2 <- ggparcoord(qt2_23,columns = c(1,3,4,5), groupColumn = 4,scale = "center")
pro_g3 <- ggparcoord(qt3_23,columns = c(1,3,4,5), groupColumn = 4,scale = "center")
pro_g4 <- ggparcoord(qt4_23,columns = c(1,3,4,5), groupColumn = 4,scale = "center")
pro_g5 <- ggparcoord(qt5_23,columns = c(1,3,4,5), groupColumn = 4,scale = "center")
ggarrange(pro_temp, pro_g1, labels = c("Template", "Graph 1"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(pro_temp, pro_g2, labels = c("Template", "Graph 2"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(pro_temp, pro_g3, labels = c("Template", "Graph 3"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(pro_temp, pro_g4, labels = c("Template", "Graph 4"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(pro_temp, pro_g5, labels = c("Template", "Graph 5"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
Removing Source and Target:
temp_1 <- ggparcoord(data = c(dt23), columns = c(4,5),groupColumn = 4 )
qt_1 <- ggparcoord(data = c(qt1_23), columns = c(4,5),groupColumn = 4 )
qt_2 <- ggparcoord(data = c(qt2_23), columns = c(4,5),groupColumn = 4 )
qt_3 <- ggparcoord(data = c(qt3_23), columns = c(4,5),groupColumn = 4 )
qt_4 <- ggparcoord(data = c(qt4_23), columns = c(4,5),groupColumn = 4 )
qt_5 <- ggparcoord(data = c(qt5_23), columns = c(4,5),groupColumn = 4 )
ggarrange(temp_1,qt_1,labels = c("Template", "Graph 1"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(temp_1,qt_2,labels = c("Template", "Graph 2"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(temp_1,qt_3,labels = c("Template", "Graph 3"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(temp_1,qt_4,labels = c("Template", "Graph 4"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
ggarrange(temp_1,qt_5,labels = c("Template", "Graph 5"), hjust = 0, vjust = 1, font.label = list(size = 10, color = "blue"))
Network Analysis:
# Communication Channel:
# For Template:
Sources <- dt01 %>%
distinct(Source) %>%
rename(label = Source)
Targets <- dt01 %>%
distinct(Target) %>%
rename(label = Target)
# Creating a Node List:
nodes <- full_join(Sources, Targets, by = "label")
nodes
## label
## 1 41
## 2 37
## 3 34
## 4 27
## 5 40
## 6 65
## 7 67
## 8 47
## 9 39
## 10 43
## 11 57
## 12 58
## 13 63
## 14 56
## 15 45
## 16 0
## 17 66
nodes <- nodes %>% rowid_to_column("id")
nodes
## id label
## 1 1 41
## 2 2 37
## 3 3 34
## 4 4 27
## 5 5 40
## 6 6 65
## 7 7 67
## 8 8 47
## 9 9 39
## 10 10 43
## 11 11 57
## 12 12 58
## 13 13 63
## 14 14 56
## 15 15 45
## 16 16 0
## 17 17 66
# Creating an Edge List:
per_route <- dt01 %>%
group_by(Source, Target) %>%
summarise(weight = n()) %>%
ungroup()
per_route
## # A tibble: 113 x 3
## Source Target weight
## <chr> <chr> <int>
## 1 27 34 8
## 2 27 37 12
## 3 27 41 9
## 4 27 43 2
## 5 27 45 1
## 6 27 47 2
## 7 27 56 2
## 8 27 57 1
## 9 27 58 2
## 10 34 27 11
## # ... with 103 more rows
edges <- per_route %>%
left_join(nodes, by = c("Source" = "label")) %>%
rename(from = id)
edges <- edges %>%
left_join(nodes, by = c("Target" = "label")) %>%
rename(to = id)
edges <- select(edges, from, to, weight)
edges
## # A tibble: 113 x 3
## from to weight
## <int> <int> <int>
## 1 4 3 8
## 2 4 2 12
## 3 4 1 9
## 4 4 10 2
## 5 4 15 1
## 6 4 8 2
## 7 4 14 2
## 8 4 11 1
## 9 4 12 2
## 10 3 4 11
## # ... with 103 more rows
# Creating a Network:
routes_network <- network(edges, vertex.attr = nodes, matrix.type = "edgelist", ignore.eval = FALSE)
class(routes_network)
## [1] "network"
routes_network
## Network attributes:
## vertices = 17
## directed = TRUE
## hyper = FALSE
## loops = FALSE
## multiple = FALSE
## bipartite = FALSE
## total edges= 113
## missing edges= 0
## non-missing edges= 113
##
## Vertex attribute names:
## id label vertex.names
##
## Edge attribute names:
## weight
# Graph 1:
Sources_G1 <- qt1 %>%
distinct(Source) %>%
rename(label = Source)
Targets_G1 <- qt1 %>%
distinct(Target) %>%
rename(label = Target)
# Creating a Node List:
nodes_G1 <- full_join(Sources_G1, Targets_G1, by = "label")
nodes_G1
## label
## 1 616050
## 2 599956
## 3 490041
## 4 533140
## 5 568093
## 6 632150
## 7 635665
## 8 512397
## 9 623295
## 10 589639
## 11 550287
## 12 550361
## 13 596193
## 14 464459
## 15 629627
## 16 599441
## 17 534034
## 18 585212
## 19 538892
## 20 542965
## 21 492777
## 22 572391
## 23 570411
## 24 640464
## 25 649553
## 26 570284
## 27 643925
## 28 608827
## 29 552988
## 30 510031
## 31 530528
## 32 635706
## 33 554431
## 34 620120
## 35 566342
## 36 548513
## 37 599057
## 38 474199
## 39 475130
## 40 576641
## 41 463777
## 42 654763
## 43 529922
## 44 599063
## 45 622296
## 46 493044
## 47 592414
## 48 575704
## 49 654981
## 50 575859
## 51 505722
## 52 517273
## 53 492286
## 54 636961
## 55 629717
## 56 502591
## 57 569820
## 58 591682
## 59 590502
## 60 559657
## 61 657187
## 62 625756
## 63 657173
## 64 509607
## 65 499467
## 66 561157
## 67 616453
## 68 630626
## 69 567195
## 70 527449
## 71 459381
## 72 595298
## 73 466907
## 74 589943
## 75 537281
## 76 580426
## 77 595581
## 78 616315
## 79 642329
## 80 503701
## 81 632961
## 82 473173
## 83 575030
## 84 621924
## 85 536346
## 86 520660
## 87 577992
## 88 571970
## 89 644226
## 90 523927
## 91 640784
## 92 503218
## 93 606730
nodes_G1 <- nodes_G1 %>% rowid_to_column("id")
nodes_G1
## id label
## 1 1 616050
## 2 2 599956
## 3 3 490041
## 4 4 533140
## 5 5 568093
## 6 6 632150
## 7 7 635665
## 8 8 512397
## 9 9 623295
## 10 10 589639
## 11 11 550287
## 12 12 550361
## 13 13 596193
## 14 14 464459
## 15 15 629627
## 16 16 599441
## 17 17 534034
## 18 18 585212
## 19 19 538892
## 20 20 542965
## 21 21 492777
## 22 22 572391
## 23 23 570411
## 24 24 640464
## 25 25 649553
## 26 26 570284
## 27 27 643925
## 28 28 608827
## 29 29 552988
## 30 30 510031
## 31 31 530528
## 32 32 635706
## 33 33 554431
## 34 34 620120
## 35 35 566342
## 36 36 548513
## 37 37 599057
## 38 38 474199
## 39 39 475130
## 40 40 576641
## 41 41 463777
## 42 42 654763
## 43 43 529922
## 44 44 599063
## 45 45 622296
## 46 46 493044
## 47 47 592414
## 48 48 575704
## 49 49 654981
## 50 50 575859
## 51 51 505722
## 52 52 517273
## 53 53 492286
## 54 54 636961
## 55 55 629717
## 56 56 502591
## 57 57 569820
## 58 58 591682
## 59 59 590502
## 60 60 559657
## 61 61 657187
## 62 62 625756
## 63 63 657173
## 64 64 509607
## 65 65 499467
## 66 66 561157
## 67 67 616453
## 68 68 630626
## 69 69 567195
## 70 70 527449
## 71 71 459381
## 72 72 595298
## 73 73 466907
## 74 74 589943
## 75 75 537281
## 76 76 580426
## 77 77 595581
## 78 78 616315
## 79 79 642329
## 80 80 503701
## 81 81 632961
## 82 82 473173
## 83 83 575030
## 84 84 621924
## 85 85 536346
## 86 86 520660
## 87 87 577992
## 88 88 571970
## 89 89 644226
## 90 90 523927
## 91 91 640784
## 92 92 503218
## 93 93 606730
# Creating an Edge List:
per_route_G1 <- qt1 %>%
group_by(Source, Target) %>%
summarise(weight = n()) %>%
ungroup()
per_route_G1
## # A tibble: 979 x 3
## Source Target weight
## <chr> <chr> <int>
## 1 463777 459381 1
## 2 463777 466907 1
## 3 463777 473173 1
## 4 463777 503701 1
## 5 463777 520660 1
## 6 463777 523927 1
## 7 463777 527449 1
## 8 463777 536346 1
## 9 463777 537281 1
## 10 463777 567195 1
## # ... with 969 more rows
edges_G1 <- per_route_G1 %>%
left_join(nodes_G1, by = c("Source" = "label")) %>%
rename(from = id)
edges_G1 <- edges_G1 %>%
left_join(nodes_G1, by = c("Target" = "label")) %>%
rename(to = id)
edges_G1 <- select(edges_G1, from, to, weight)
edges_G1
## # A tibble: 979 x 3
## from to weight
## <int> <int> <int>
## 1 41 71 1
## 2 41 73 1
## 3 41 82 1
## 4 41 80 1
## 5 41 86 1
## 6 41 90 1
## 7 41 70 1
## 8 41 85 1
## 9 41 75 1
## 10 41 69 1
## # ... with 969 more rows
# Creating a Network:
routes_network_G1 <- network(edges_G1, vertex.attr = nodes_G1, matrix.type = "edgelist", ignore.eval = FALSE)
routes_network_G1
## Network attributes:
## vertices = 93
## directed = TRUE
## hyper = FALSE
## loops = FALSE
## multiple = FALSE
## bipartite = FALSE
## total edges= 979
## missing edges= 0
## non-missing edges= 979
##
## Vertex attribute names:
## id label vertex.names
##
## Edge attribute names:
## weight
# Graph 2:
Sources_G2 <- qt2 %>%
distinct(Source) %>%
rename(label = Source)
Targets_G2 <- qt2 %>%
distinct(Target) %>%
rename(label = Target)
# Creating a Node List:
nodes_G2 <- full_join(Sources_G2, Targets_G2, by = "label")
nodes_G2
## label
## 1 563211
## 2 541017
## 3 572413
## 4 505965
## 5 629627
## 6 515794
## 7 585212
## 8 599441
## 9 582851
## 10 527597
## 11 534034
## 12 644830
## 13 488928
## 14 602912
## 15 477138
## 16 544615
## 17 534449
## 18 639051
## 19 572391
## 20 542965
## 21 635665
## 22 538892
## 23 464459
## 24 568093
## 25 604021
## 26 510031
## 27 552988
## 28 533094
## 29 606043
## 30 595057
## 31 634181
## 32 548320
## 33 563584
## 34 536953
## 35 620120
## 36 515799
## 37 656156
## 38 552439
## 39 546478
## 40 533024
## 41 499312
## 42 464563
## 43 546626
## 44 533141
## 45 471663
## 46 501047
## 47 472522
## 48 475811
## 49 590265
## 50 653390
## 51 573870
## 52 645210
## 53 564798
## 54 627390
## 55 561114
## 56 601492
## 57 487668
## 58 657173
## 59 625756
## 60 509607
## 61 499467
## 62 630626
## 63 536346
## 64 520660
## 65 527449
## 66 459381
## 67 595298
## 68 466907
## 69 577992
## 70 580426
## 71 595581
## 72 616315
## 73 503701
## 74 571970
## 75 644226
## 76 632961
## 77 473173
## 78 575030
## 79 621924
## 80 640784
## 81 567195
## 82 537281
## 83 523927
## 84 642329
## 85 589943
## 86 503218
## 87 606730
nodes_G2 <- nodes_G2 %>% rowid_to_column("id")
nodes_G2
## id label
## 1 1 563211
## 2 2 541017
## 3 3 572413
## 4 4 505965
## 5 5 629627
## 6 6 515794
## 7 7 585212
## 8 8 599441
## 9 9 582851
## 10 10 527597
## 11 11 534034
## 12 12 644830
## 13 13 488928
## 14 14 602912
## 15 15 477138
## 16 16 544615
## 17 17 534449
## 18 18 639051
## 19 19 572391
## 20 20 542965
## 21 21 635665
## 22 22 538892
## 23 23 464459
## 24 24 568093
## 25 25 604021
## 26 26 510031
## 27 27 552988
## 28 28 533094
## 29 29 606043
## 30 30 595057
## 31 31 634181
## 32 32 548320
## 33 33 563584
## 34 34 536953
## 35 35 620120
## 36 36 515799
## 37 37 656156
## 38 38 552439
## 39 39 546478
## 40 40 533024
## 41 41 499312
## 42 42 464563
## 43 43 546626
## 44 44 533141
## 45 45 471663
## 46 46 501047
## 47 47 472522
## 48 48 475811
## 49 49 590265
## 50 50 653390
## 51 51 573870
## 52 52 645210
## 53 53 564798
## 54 54 627390
## 55 55 561114
## 56 56 601492
## 57 57 487668
## 58 58 657173
## 59 59 625756
## 60 60 509607
## 61 61 499467
## 62 62 630626
## 63 63 536346
## 64 64 520660
## 65 65 527449
## 66 66 459381
## 67 67 595298
## 68 68 466907
## 69 69 577992
## 70 70 580426
## 71 71 595581
## 72 72 616315
## 73 73 503701
## 74 74 571970
## 75 75 644226
## 76 76 632961
## 77 77 473173
## 78 78 575030
## 79 79 621924
## 80 80 640784
## 81 81 567195
## 82 82 537281
## 83 83 523927
## 84 84 642329
## 85 85 589943
## 86 86 503218
## 87 87 606730
# Creating an Edge List:
per_route_G2 <- qt2 %>%
group_by(Source, Target) %>%
summarise(weight = n()) %>%
ungroup()
per_route_G2
## # A tibble: 952 x 3
## Source Target weight
## <chr> <chr> <int>
## 1 464459 499467 1
## 2 464459 625756 1
## 3 464563 459381 1
## 4 464563 466907 1
## 5 464563 473173 1
## 6 464563 503701 1
## 7 464563 520660 1
## 8 464563 523927 1
## 9 464563 527449 1
## 10 464563 536346 1
## # ... with 942 more rows
edges_G2 <- per_route_G2 %>%
left_join(nodes_G2, by = c("Source" = "label")) %>%
rename(from = id)
edges_G2 <- edges_G2 %>%
left_join(nodes_G2, by = c("Target" = "label")) %>%
rename(to = id)
edges_G2 <- select(edges_G2, from, to, weight)
edges_G2
## # A tibble: 952 x 3
## from to weight
## <int> <int> <int>
## 1 23 61 1
## 2 23 59 1
## 3 42 66 1
## 4 42 68 1
## 5 42 77 1
## 6 42 73 1
## 7 42 64 1
## 8 42 83 1
## 9 42 65 1
## 10 42 63 1
## # ... with 942 more rows
# Creating a Network:
routes_network_G2 <- network(edges_G2, vertex.attr = nodes_G2, matrix.type = "edgelist", ignore.eval = FALSE)
routes_network_G2
## Network attributes:
## vertices = 87
## directed = TRUE
## hyper = FALSE
## loops = FALSE
## multiple = FALSE
## bipartite = FALSE
## total edges= 952
## missing edges= 0
## non-missing edges= 952
##
## Vertex attribute names:
## id label vertex.names
##
## Edge attribute names:
## weight
# Graph 3:
Sources_G3 <- qt3 %>%
distinct(Source) %>%
rename(label = Source)
Targets_G3 <- qt3 %>%
distinct(Target) %>%
rename(label = Target)
# Creating a Node List:
nodes_G3 <- full_join(Sources_G3, Targets_G3, by = "label")
nodes_G3
## label
## 1 614761
## 2 538892
## 3 500813
## 4 493094
## 5 536003
## 6 521318
## 7 542649
## 8 572391
## 9 541619
## 10 544074
## 11 493652
## 12 516236
## 13 607386
## 14 629627
## 15 585212
## 16 534034
## 17 599441
## 18 542965
## 19 635665
## 20 568093
## 21 464459
## 22 570284
## 23 643925
## 24 649553
## 25 598006
## 26 612711
## 27 643411
## 28 610497
## 29 552988
## 30 578531
## 31 510031
## 32 657076
## 33 478754
## 34 575295
## 35 568284
## 36 508898
## 37 620120
## 38 536951
## 39 466976
## 40 628223
## 41 492701
## 42 584736
## 43 520084
## 44 529433
## 45 604113
## 46 514306
## 47 476813
## 48 657173
## 49 625756
## 50 509607
## 51 499467
## 52 561157
## 53 616453
## 54 640784
## 55 630626
## 56 567195
## 57 527449
## 58 459381
## 59 595298
## 60 466907
## 61 589943
## 62 537281
## 63 523927
## 64 580426
## 65 616315
## 66 503701
## 67 632961
## 68 473173
## 69 575030
## 70 503218
## 71 606730
## 72 577992
## 73 642329
## 74 621924
## 75 571970
## 76 595581
## 77 536346
## 78 520660
## 79 644226
nodes_G3 <- nodes_G3 %>% rowid_to_column("id")
nodes_G3
## id label
## 1 1 614761
## 2 2 538892
## 3 3 500813
## 4 4 493094
## 5 5 536003
## 6 6 521318
## 7 7 542649
## 8 8 572391
## 9 9 541619
## 10 10 544074
## 11 11 493652
## 12 12 516236
## 13 13 607386
## 14 14 629627
## 15 15 585212
## 16 16 534034
## 17 17 599441
## 18 18 542965
## 19 19 635665
## 20 20 568093
## 21 21 464459
## 22 22 570284
## 23 23 643925
## 24 24 649553
## 25 25 598006
## 26 26 612711
## 27 27 643411
## 28 28 610497
## 29 29 552988
## 30 30 578531
## 31 31 510031
## 32 32 657076
## 33 33 478754
## 34 34 575295
## 35 35 568284
## 36 36 508898
## 37 37 620120
## 38 38 536951
## 39 39 466976
## 40 40 628223
## 41 41 492701
## 42 42 584736
## 43 43 520084
## 44 44 529433
## 45 45 604113
## 46 46 514306
## 47 47 476813
## 48 48 657173
## 49 49 625756
## 50 50 509607
## 51 51 499467
## 52 52 561157
## 53 53 616453
## 54 54 640784
## 55 55 630626
## 56 56 567195
## 57 57 527449
## 58 58 459381
## 59 59 595298
## 60 60 466907
## 61 61 589943
## 62 62 537281
## 63 63 523927
## 64 64 580426
## 65 65 616315
## 66 66 503701
## 67 67 632961
## 68 68 473173
## 69 69 575030
## 70 70 503218
## 71 71 606730
## 72 72 577992
## 73 73 642329
## 74 74 621924
## 75 75 571970
## 76 76 595581
## 77 77 536346
## 78 78 520660
## 79 79 644226
# Creating an Edge List:
per_route_G3 <- qt3 %>%
group_by(Source, Target) %>%
summarise(weight = n()) %>%
ungroup()
per_route_G3
## # A tibble: 606 x 3
## Source Target weight
## <chr> <chr> <int>
## 1 464459 499467 1
## 2 464459 625756 1
## 3 466976 459381 1
## 4 466976 466907 1
## 5 466976 473173 1
## 6 466976 503701 1
## 7 466976 523927 1
## 8 466976 527449 1
## 9 466976 537281 1
## 10 466976 571970 1
## # ... with 596 more rows
edges_G3 <- per_route_G3 %>%
left_join(nodes_G3, by = c("Source" = "label")) %>%
rename(from = id)
edges_G3 <- edges_G3 %>%
left_join(nodes_G3, by = c("Target" = "label")) %>%
rename(to = id)
edges_G3 <- select(edges_G3, from, to, weight)
edges_G3
## # A tibble: 606 x 3
## from to weight
## <int> <int> <int>
## 1 21 51 1
## 2 21 49 1
## 3 39 58 1
## 4 39 60 1
## 5 39 68 1
## 6 39 66 1
## 7 39 63 1
## 8 39 57 1
## 9 39 62 1
## 10 39 75 1
## # ... with 596 more rows
# Creating a Network:
routes_network_G3 <- network(edges_G3, vertex.attr = nodes_G3, matrix.type = "edgelist", ignore.eval = FALSE)
routes_network_G3
## Network attributes:
## vertices = 79
## directed = TRUE
## hyper = FALSE
## loops = FALSE
## multiple = FALSE
## bipartite = FALSE
## total edges= 606
## missing edges= 0
## non-missing edges= 606
##
## Vertex attribute names:
## id label vertex.names
##
## Edge attribute names:
## weight
# Graph 4:
Sources_G4 <- qt4 %>%
distinct(Source) %>%
rename(label = Source)
Targets_G4 <- qt4 %>%
distinct(Target) %>%
rename(label = Target)
# Creating a Node List:
nodes_G4 <- full_join(Sources_G4, Targets_G4, by = "label")
nodes_G4
## label
## 1 636721
## 2 628320
## 3 546593
## 4 536906
## 5 483005
## 6 601496
## 7 580798
## 8 492850
## 9 639642
## 10 557269
## 11 579305
## 12 584457
## 13 516873
## 14 569329
## 15 544636
## 16 464579
## 17 482012
## 18 566580
## 19 657526
## 20 588172
## 21 585606
## 22 655963
## 23 541907
## 24 510031
## 25 552988
## 26 620120
## 27 571369
## 28 477374
## 29 585417
## 30 625756
## 31 461577
## 32 629826
## 33 618398
## 34 655265
## 35 588802
## 36 499177
## 37 611572
## 38 561157
## 39 509607
## 40 580237
## 41 482579
## 42 638734
## 43 596726
## 44 537816
## 45 557626
## 46 657173
## 47 558089
## 48 459726
## 49 499467
## 50 578749
## 51 492039
## 52 571670
## 53 616453
## 54 500336
## 55 605235
## 56 623468
## 57 611238
## 58 590595
## 59 521673
## 60 516393
## 61 645371
## 62 536346
## 63 567195
## 64 527449
## 65 459381
## 66 595298
## 67 466907
## 68 577992
## 69 537281
## 70 523927
## 71 595581
## 72 642329
## 73 503701
## 74 571970
## 75 644226
## 76 632961
## 77 473173
## 78 575030
## 79 630626
## 80 580426
## 81 616315
## 82 520660
## 83 589943
## 84 606730
## 85 621924
## 86 503218
## 87 640784
nodes_G4 <- nodes_G4 %>% rowid_to_column("id")
nodes_G4
## id label
## 1 1 636721
## 2 2 628320
## 3 3 546593
## 4 4 536906
## 5 5 483005
## 6 6 601496
## 7 7 580798
## 8 8 492850
## 9 9 639642
## 10 10 557269
## 11 11 579305
## 12 12 584457
## 13 13 516873
## 14 14 569329
## 15 15 544636
## 16 16 464579
## 17 17 482012
## 18 18 566580
## 19 19 657526
## 20 20 588172
## 21 21 585606
## 22 22 655963
## 23 23 541907
## 24 24 510031
## 25 25 552988
## 26 26 620120
## 27 27 571369
## 28 28 477374
## 29 29 585417
## 30 30 625756
## 31 31 461577
## 32 32 629826
## 33 33 618398
## 34 34 655265
## 35 35 588802
## 36 36 499177
## 37 37 611572
## 38 38 561157
## 39 39 509607
## 40 40 580237
## 41 41 482579
## 42 42 638734
## 43 43 596726
## 44 44 537816
## 45 45 557626
## 46 46 657173
## 47 47 558089
## 48 48 459726
## 49 49 499467
## 50 50 578749
## 51 51 492039
## 52 52 571670
## 53 53 616453
## 54 54 500336
## 55 55 605235
## 56 56 623468
## 57 57 611238
## 58 58 590595
## 59 59 521673
## 60 60 516393
## 61 61 645371
## 62 62 536346
## 63 63 567195
## 64 64 527449
## 65 65 459381
## 66 66 595298
## 67 67 466907
## 68 68 577992
## 69 69 537281
## 70 70 523927
## 71 71 595581
## 72 72 642329
## 73 73 503701
## 74 74 571970
## 75 75 644226
## 76 76 632961
## 77 77 473173
## 78 78 575030
## 79 79 630626
## 80 80 580426
## 81 81 616315
## 82 82 520660
## 83 83 589943
## 84 84 606730
## 85 85 621924
## 86 86 503218
## 87 87 640784
# Creating an Edge List:
per_route_G4 <- qt4 %>%
group_by(Source, Target) %>%
summarise(weight = n()) %>%
ungroup()
per_route_G4
## # A tibble: 615 x 3
## Source Target weight
## <chr> <chr> <int>
## 1 464579 459381 1
## 2 464579 459726 1
## 3 464579 466907 1
## 4 464579 473173 1
## 5 464579 500336 1
## 6 464579 503701 1
## 7 464579 516393 1
## 8 464579 521673 1
## 9 464579 523927 1
## 10 464579 527449 1
## # ... with 605 more rows
edges_G4 <- per_route_G4 %>%
left_join(nodes_G4, by = c("Source" = "label")) %>%
rename(from = id)
edges_G4 <- edges_G4 %>%
left_join(nodes_G4, by = c("Target" = "label")) %>%
rename(to = id)
edges_G4 <- select(edges_G4, from, to, weight)
edges_G4
## # A tibble: 615 x 3
## from to weight
## <int> <int> <int>
## 1 16 65 1
## 2 16 48 1
## 3 16 67 1
## 4 16 77 1
## 5 16 54 1
## 6 16 73 1
## 7 16 60 1
## 8 16 59 1
## 9 16 70 1
## 10 16 64 1
## # ... with 605 more rows
# Creating a Network:
routes_network_G4 <- network(edges_G4, vertex.attr = nodes_G4, matrix.type = "edgelist", ignore.eval = FALSE)
routes_network_G4
## Network attributes:
## vertices = 87
## directed = TRUE
## hyper = FALSE
## loops = FALSE
## multiple = FALSE
## bipartite = FALSE
## total edges= 615
## missing edges= 0
## non-missing edges= 615
##
## Vertex attribute names:
## id label vertex.names
##
## Edge attribute names:
## weight
# Graph 5:
Sources_G5 <- qt5 %>%
distinct(Source) %>%
rename(label = Source)
Targets_G5 <- qt5 %>%
distinct(Target) %>%
rename(label = Target)
# Creating a Node List:
nodes_G5 <- full_join(Sources_G5, Targets_G5, by = "label")
nodes_G5
## label
## 1 619322
## 2 594308
## 3 524153
## 4 483784
## 5 549840
## 6 477657
## 7 631903
## 8 573137
## 9 561819
## 10 530990
## 11 510031
## 12 552988
## 13 620120
## 14 590442
## 15 629769
## 16 461577
## 17 547205
## 18 549891
## 19 632485
## 20 657173
## 21 620947
## 22 492039
## 23 616453
## 24 483999
## 25 644754
## 26 525263
## 27 532852
## 28 625756
## 29 517649
## 30 509607
## 31 587437
## 32 623736
## 33 493358
## 34 561157
## 35 643087
## 36 569044
## 37 556592
## 38 585589
## 39 579218
## 40 567281
## 41 624532
## 42 499177
## 43 605235
## 44 641131
## 45 499467
## 46 654641
## 47 620076
## 48 652996
## 49 558930
## 50 469675
## 51 657035
## 52 590595
## 53 529694
## 54 528019
## 55 472749
## 56 550251
## 57 619245
## 58 584229
## 59 544444
## 60 555931
## 61 503218
## 62 536346
## 63 520660
## 64 567195
## 65 527449
## 66 459381
## 67 595298
## 68 466907
## 69 589943
## 70 577992
## 71 537281
## 72 523927
## 73 580426
## 74 595581
## 75 616315
## 76 642329
## 77 503701
## 78 571970
## 79 644226
## 80 632961
## 81 473173
## 82 575030
## 83 621924
## 84 640784
## 85 630626
## 86 606730
nodes_G5 <- nodes_G5 %>% rowid_to_column("id")
nodes_G5
## id label
## 1 1 619322
## 2 2 594308
## 3 3 524153
## 4 4 483784
## 5 5 549840
## 6 6 477657
## 7 7 631903
## 8 8 573137
## 9 9 561819
## 10 10 530990
## 11 11 510031
## 12 12 552988
## 13 13 620120
## 14 14 590442
## 15 15 629769
## 16 16 461577
## 17 17 547205
## 18 18 549891
## 19 19 632485
## 20 20 657173
## 21 21 620947
## 22 22 492039
## 23 23 616453
## 24 24 483999
## 25 25 644754
## 26 26 525263
## 27 27 532852
## 28 28 625756
## 29 29 517649
## 30 30 509607
## 31 31 587437
## 32 32 623736
## 33 33 493358
## 34 34 561157
## 35 35 643087
## 36 36 569044
## 37 37 556592
## 38 38 585589
## 39 39 579218
## 40 40 567281
## 41 41 624532
## 42 42 499177
## 43 43 605235
## 44 44 641131
## 45 45 499467
## 46 46 654641
## 47 47 620076
## 48 48 652996
## 49 49 558930
## 50 50 469675
## 51 51 657035
## 52 52 590595
## 53 53 529694
## 54 54 528019
## 55 55 472749
## 56 56 550251
## 57 57 619245
## 58 58 584229
## 59 59 544444
## 60 60 555931
## 61 61 503218
## 62 62 536346
## 63 63 520660
## 64 64 567195
## 65 65 527449
## 66 66 459381
## 67 67 595298
## 68 68 466907
## 69 69 589943
## 70 70 577992
## 71 71 537281
## 72 72 523927
## 73 73 580426
## 74 74 595581
## 75 75 616315
## 76 76 642329
## 77 77 503701
## 78 78 571970
## 79 79 644226
## 80 80 632961
## 81 81 473173
## 82 82 575030
## 83 83 621924
## 84 84 640784
## 85 85 630626
## 86 86 606730
# Creating an Edge List:
per_route_G5 <- qt5 %>%
group_by(Source, Target) %>%
summarise(weight = n()) %>%
ungroup()
per_route_G5
## # A tibble: 285 x 3
## Source Target weight
## <chr> <chr> <int>
## 1 477657 459381 1
## 2 477657 466907 1
## 3 477657 473173 1
## 4 477657 499467 5
## 5 477657 503701 1
## 6 477657 527449 1
## 7 477657 561157 5
## 8 477657 561819 1
## 9 477657 567195 1
## 10 477657 571970 1
## # ... with 275 more rows
edges_G5 <- per_route_G5 %>%
left_join(nodes_G5, by = c("Source" = "label")) %>%
rename(from = id)
edges_G5 <- edges_G5 %>%
left_join(nodes_G5, by = c("Target" = "label")) %>%
rename(to = id)
edges_G5 <- select(edges_G5, from, to, weight)
edges_G5
## # A tibble: 285 x 3
## from to weight
## <int> <int> <int>
## 1 6 66 1
## 2 6 68 1
## 3 6 81 1
## 4 6 45 5
## 5 6 77 1
## 6 6 65 1
## 7 6 34 5
## 8 6 9 1
## 9 6 64 1
## 10 6 78 1
## # ... with 275 more rows
# Creating a Network:
routes_network_G5 <- network(edges_G5, vertex.attr = nodes_G5, matrix.type = "edgelist", ignore.eval = FALSE)
routes_network_G5
## Network attributes:
## vertices = 86
## directed = TRUE
## hyper = FALSE
## loops = FALSE
## multiple = FALSE
## bipartite = FALSE
## total edges= 285
## missing edges= 0
## non-missing edges= 285
##
## Vertex attribute names:
## id label vertex.names
##
## Edge attribute names:
## weight
Network Visualisation:
plot(routes_network, vertex.cex = 3, main = "Template")
plot(routes_network_G1, vertex.cex = 3, main = "Graph 1")
plot(routes_network_G2, vertex.cex = 3, main = "Graph 2")
plot(routes_network_G3, vertex.cex = 3, main = "Graph 3")
plot(routes_network_G4, vertex.cex = 3, main = "Graph 4")
plot(routes_network_G5, vertex.cex = 3, main = "Graph 5")
Interactive Network Analysis:
VisNetwork:
# Communication Channel:
# Weighted edges:
edges <- mutate(edges, width = weight/5 + 1)
edges_G1 <- mutate(edges_G1, width = weight/5 + 1)
edges_G2 <- mutate(edges_G2, width = weight/5 + 1)
edges_G3 <- mutate(edges_G3, width = weight/5 + 1)
edges_G4 <- mutate(edges_G4, width = weight/5 + 1)
edges_G5 <- mutate(edges_G5, width = weight/5 + 1)
# Interactive Graphs with visNetwork:
temp_com <- visNetwork(nodes, edges)%>% visIgraphLayout(layout = "layout_with_fr") %>% visEdges(arrows = "middle")
visPhysics(temp_com, stabilization = FALSE, enabled = FALSE)
g1_com <- visNetwork(nodes_G1, edges_G1)%>% visIgraphLayout(layout = "layout_with_fr") %>% visEdges(arrows = "middle")
visPhysics(g1_com, stabilization = FALSE, enabled = FALSE)
g2_com <- visNetwork(nodes_G2, edges_G2)%>% visIgraphLayout(layout = "layout_with_fr") %>% visEdges(arrows = "middle")
visPhysics(g2_com, stabilization = FALSE, enabled = FALSE)
g3_com <- visNetwork(nodes_G3, edges_G3)%>% visIgraphLayout(layout = "layout_with_fr") %>% visEdges(arrows = "middle")
visPhysics(g3_com, stabilization = FALSE, enabled = FALSE)
g4_com <- visNetwork(nodes_G4, edges_G4)%>% visIgraphLayout(layout = "layout_with_fr") %>% visEdges(arrows = "middle")
visPhysics(g4_com, stabilization = FALSE, enabled = FALSE)
g5_com <- visNetwork(nodes_G5, edges_G5)%>% visIgraphLayout(layout = "layout_with_fr") %>% visEdges(arrows = "middle")
visPhysics(g5_com, stabilization = FALSE, enabled = FALSE)
Network D3.js
# Network D3.js:
nodes_d3 <- mutate(nodes, id = id - 1)
edges_d3 <- mutate(edges, from = from - 1, to = to - 1)
forceNetwork(Links = edges_d3, Nodes = nodes_d3, Source = "from", Target = "to",
NodeID = "label", Group = "id", Value = "weight",
opacity = 1, fontSize = 16, zoom = TRUE)
## Links is a tbl_df. Converting to a plain data frame.
nodes_d3_g1 <- mutate(nodes_G1, id = id - 1)
edges_d3_g1 <- mutate(edges_G1, from = from - 1, to = to - 1)
forceNetwork(Links = edges_d3_g1, Nodes = nodes_d3_g1, Source = "from", Target = "to",
NodeID = "label", Group = "id", Value = "weight",
opacity = 1, fontSize = 16, zoom = TRUE)
## Links is a tbl_df. Converting to a plain data frame.
nodes_d3_g2 <- mutate(nodes_G2, id = id - 1)
edges_d3_g2 <- mutate(edges_G2, from = from - 1, to = to - 1)
forceNetwork(Links = edges_d3_g2, Nodes = nodes_d3_g2, Source = "from", Target = "to",
NodeID = "label", Group = "id", Value = "weight",
opacity = 1, fontSize = 16, zoom = TRUE)
## Links is a tbl_df. Converting to a plain data frame.
nodes_d3_g3 <- mutate(nodes_G3, id = id - 1)
edges_d3_g3 <- mutate(edges_G3, from = from - 1, to = to - 1)
forceNetwork(Links = edges_d3_g3, Nodes = nodes_d3_g3, Source = "from", Target = "to",
NodeID = "label", Group = "id", Value = "weight",
opacity = 1, fontSize = 16, zoom = TRUE)
## Links is a tbl_df. Converting to a plain data frame.
nodes_d3_g4 <- mutate(nodes_G4, id = id - 1)
edges_d3_g4 <- mutate(edges_G4, from = from - 1, to = to - 1)
forceNetwork(Links = edges_d3_g4, Nodes = nodes_d3_g4, Source = "from", Target = "to",
NodeID = "label", Group = "id", Value = "weight",
opacity = 1, fontSize = 16, zoom = TRUE)
## Links is a tbl_df. Converting to a plain data frame.
nodes_d3_g5 <- mutate(nodes_G5, id = id - 1)
edges_d3_g5 <- mutate(edges_G5, from = from - 1, to = to - 1)
forceNetwork(Links = edges_d3_g5, Nodes = nodes_d3_g5, Source = "from", Target = "to",
NodeID = "label", Group = "id", Value = "weight",
opacity = 1, fontSize = 16, zoom = TRUE)
## Links is a tbl_df. Converting to a plain data frame.
Skankey Network:
sankeyNetwork(Links = edges_d3, Nodes = nodes_d3, Source = "from", Target = "to",
NodeID = "label", Value = "weight", fontSize = 16, unit = "Node(s)")
## Links is a tbl_df. Converting to a plain data frame.
sankeyNetwork(Links = edges_d3_g1, Nodes = nodes_d3_g1, Source = "from", Target = "to",
NodeID = "label", Value = "weight", fontSize = 16, unit = "Node(s)")
## Links is a tbl_df. Converting to a plain data frame.
sankeyNetwork(Links = edges_d3_g2, Nodes = nodes_d3_g2, Source = "from", Target = "to",
NodeID = "label", Value = "weight", fontSize = 16, unit = "Node(s)")
## Links is a tbl_df. Converting to a plain data frame.
sankeyNetwork(Links = edges_d3_g3, Nodes = nodes_d3_g3, Source = "from", Target = "to",
NodeID = "label", Value = "weight", fontSize = 16, unit = "Node(s)")
## Links is a tbl_df. Converting to a plain data frame.
sankeyNetwork(Links = edges_d3_g4, Nodes = nodes_d3_g4, Source = "from", Target = "to",
NodeID = "label", Value = "weight", fontSize = 16, unit = "Node(s)")
## Links is a tbl_df. Converting to a plain data frame.
sankeyNetwork(Links = edges_d3_g4, Nodes = nodes_d3_g4, Source = "from", Target = "to",
NodeID = "label", Value = "weight", fontSize = 16, unit = "Node(s)")
## Links is a tbl_df. Converting to a plain data frame.